© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128513
    Prev
    Next
    INDEX
    Explanations

    topic of discussion

    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
     for
    -1.45
     people
    -1.31
     from
    -1.29
     of
    -1.28
     first
    -1.20
     at
    -1.20
     or
    -1.18
     Without
    -1.17
    參考文獻
    -1.16
     during
    -1.16
    POSITIVE LOGITS
     whether
    1.52
     COMMUNIC
    1.38
    がなく
    1.35
     việc
    1.31
    icona
    1.24
     this
    1.23
    棡
    1.23
     whom
    1.22
     its
    1.21
     INGREDIENTS
    1.21
    Activations Density 0.039%

    No Known Activations