© 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. 22-GEMMASCOPE-RES-131K
    7. 15701
    Prev
    Next
    INDEX
    Explanations

    installing software packages

    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
    mathrm
    -1.95
     denselben
    -1.45
    _
    -1.45
     evtl
    -1.45
    ↵↵↵
    -1.40
     unmittelbar
    -1.40
     irgende
    -1.35
    ;\\
    -1.35
     letzt
    -1.34
     möglicherweise
    -1.31
    POSITIVE LOGITS
     in
    1.62
    RemindMe
    1.50
     from
    1.41
    жели
    1.38
     without
    1.34
     Вене
    1.26
     noro
    1.25
     bertambah
    1.25
     САД
    1.25
    danke
    1.24
    Activations Density 0.058%

    No Known Activations