© 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. 26253
    Prev
    Next
    INDEX
    Explanations

    cannot do this

    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
     which
    -1.02
    Londres
    -0.96
    也不用
    -0.95
    כט
    -0.93
     however
    -0.92
    焄
    -0.91
     sollte
    -0.90
    zulka
    -0.90
    Sonntag
    -0.89
     Sorge
    -0.89
    POSITIVE LOGITS
     already
    1.51
    Already
    1.16
     cannot
    1.12
    already
    1.04
    aip
    0.98
     locked
    0.97
    izade
    0.97
     Modèle
    0.96
    Cannot
    0.95
     redan
    0.95
    Activations Density 0.179%

    No Known Activations