© 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. 22-GEMMASCOPE-RES-131K
    7. 71050
    Prev
    Next
    INDEX
    Explanations

    initial tokenization

    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
    middels
    -1.30
    EdgeInsets
    -1.19
    IVENESS
    -1.16
    Год
    -1.16
     its
    -1.16
    懸命
    -1.07
     кухне
    -1.05
     reçu
    -1.04
     artista
    -1.03
    RICULUM
    -1.03
    POSITIVE LOGITS
    .
    1.12
     først
    1.09
     Firstly
    1.06
     firstly
    1.06
    Firstly
    1.02
    ucks
    0.99
    ,
    0.99
     appunto
    0.98
     Phila
    0.97
     omtrent
    0.97
    Activations Density 0.000%

    No Known Activations