© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75018
    Prev
    Next
    INDEX
    Explanations

    Gamma irradiation

    np_acts-logits-general · gemini-2.5-flash-lite

    numerical identifiers or codes in technical or legal documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron spikes on brief alphanumeric identifiers—like regulation section numbers (e.g. “23”) or service acronyms (e.g. “waf”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fahrzeuge
    -1.26
     Благодаря
    -1.15
     its
    -1.13
     Bewußt
    -1.13
     lixo
    -1.10
     famosa
    -1.09
     прось
    -1.09
     benö
    -1.06
     myself
    -1.05
     großzü
    -1.05
    POSITIVE LOGITS
    arkhand
    1.21
    ländischen
    1.15
    もありました
    1.13
     туристи
    1.09
    蔼
    1.08
     for
    1.06
    Grath
    1.06
     nM
    1.05
    Geografi
    1.05
    焼け
    1.05
    Activations Density 0.000%

    No Known Activations