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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11480
    Prev
    Next
    INDEX
    Explanations

    Sebastian Siebrecht or Q:

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     menik
    -1.79
     menyen
    -1.77
     époux
    -1.74
     jika
    -1.69
     in
    -1.69
    2
    -1.66
     because
    -1.66
    蚍
    -1.65
     作り方
    -1.65
    Would
    -1.64
    POSITIVE LOGITS
    .''
    1.88
    an
    1.84
    ot
    1.73
    Y
    1.71
    ou
    1.70
    are
    1.67
    ut
    1.66
     brilliantly
    1.63
    ns
    1.63
    ne
    1.59
    Activations Density 0.000%

    No Known Activations