© 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. 71603
    Prev
    Next
    INDEX
    Explanations

    legal, technical, and academic contexts

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

    The neuron is primarily triggered by short alphanumeric code tokens (identifiers or format‐specifier fragments) of just a few characters.

    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
     nastro
    -1.30
    だけではなく
    -1.30
     manifiesta
    -1.30
     actief
    -1.29
    為に
    -1.28
     belangrijk
    -1.27
    筈
    -1.26
    yyj
    -1.24
     along
    -1.24
     reconoce
    -1.23
    POSITIVE LOGITS
    Because
    1.71
    If
    1.67
     if
    1.44
     new
    1.40
     statunit
    1.38
    Более
    1.24
    because
    1.23
    Having
    1.22
    ！");
    1.20
    Get
    1.20
    Activations Density 0.000%

    No Known Activations