© 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. 79965
    Prev
    Next
    INDEX
    Explanations

    introduces examples or lists

    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
    マジで
    -1.32
    こっち
    -1.27
    こいつ
    -1.26
    割と
    -1.23
    あぁ
    -1.23
    凄く
    -1.22
    ごめん
    -1.22
    おまけ
    -1.21
     fotovolta
    -1.20
    ガチ
    -1.20
    POSITIVE LOGITS
     any
    1.91
     through
    1.59
     during
    1.54
     from
    1.51
     in
    1.43
     those
    1.41
     after
    1.41
     taking
    1.38
     but
    1.38
     for
    1.34
    Activations Density 0.072%

    No Known Activations