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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38625
    Prev
    Next
    INDEX
    Explanations

    Compiler, balanced, circular, decoder

    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
     of
    -3.89
     in
    -3.48
    ですが
    -2.91
     on
    -2.56
     by
    -2.47
    もある
    -2.47
     at
    -2.42
    を
    -2.25
    しますが
    -2.25
    ですので
    -2.25
    POSITIVE LOGITS
    為に
    2.94
    久し
    2.58
    を行い
    2.41
    に入れる
    2.36
    の商品
    2.28
    際には
    2.25
    ところに
    2.20
    さぁ
    2.19
    ことも
    2.19
    明日は
    2.17
    Activations Density 0.039%

    No Known Activations