© 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. 10-GEMMASCOPE-RES-131K
    7. 40778
    Prev
    Next
    INDEX
    Explanations

    no one / nobody / not

    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_10/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
    ,
    -1.37
    despite
    -1.24
    presumably
    -1.23
     execução
    -1.20
     碎
    -1.19
     والق
    -1.19
     repeti
    -1.17
    providing
    -1.16
     juu
    -1.16
    だけでなく
    -1.16
    POSITIVE LOGITS
     this
    1.92
     their
    1.68
     a
    1.57
     because
    1.32
     from
    1.31
     mereka
    1.31
    ！(
    1.30
    ²(
    1.24
     these
    1.23
     Ruß
    1.23
    Activations Density 0.106%

    No Known Activations