© 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. 33406
    Prev
    Next
    INDEX
    Explanations

    technical context

    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
     like
    -1.29
     their
    -1.28
     I
    -1.19
     all
    -1.14
     on
    -1.14
     falda
    -1.11
     most
    -1.10
     this
    -1.09
     it
    -1.08
     nagu
    -1.06
    POSITIVE LOGITS
    middelen
    1.17
    Similarly
    1.16
    Encu
    1.16
    küche
    1.15
    ויות
    1.14
    incontro
    1.13
     imparare
    1.13
    Colore
    1.12
    EDITORIAL
    1.10
    Curios
    1.10
    Activations Density 0.000%

    No Known Activations