© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40068
    Prev
    Next
    INDEX
    Explanations

    previous and next

    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
    ruiter
    -1.33
     również
    -1.30
    Président
    -1.26
    Again
    -1.24
     נוספת
    -1.23
     ofrecer
    -1.22
    icolon
    -1.22
     マフラー
    -1.22
    Associazione
    -1.22
    ribune
    -1.21
    POSITIVE LOGITS
     some
    1.66
     некоторых
    1.55
     "..\..\
    1.34
     někter
    1.34
    ）」
    1.34
    ’
    1.32
    {~
    1.29
     being
    1.24
     что
    1.23
     when
    1.20
    Activations Density 0.026%

    No Known Activations