© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70642
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    The neuron flags programming‐style identifiers (e.g. variable names, function names, include paths) typically containing underscores or file extensions.

    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
    趿
    -1.14
     accompagner
    -1.09
     vingt
    -1.05
     perda
    -1.03
     inond
    -1.02
    springen
    -1.02
     kado
    -1.02
    BOTH
    -1.02
    sver
    -1.02
     corriger
    -1.00
    POSITIVE LOGITS
     get
    1.33
     our
    1.32
     new
    1.23
     first
    1.06
     talked
    1.05
     powy
    1.00
     before
    0.99
     told
    0.98
     with
    0.96
     described
    0.96
    Activations Density 0.001%

    No Known Activations