© 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. 21446
    Prev
    Next
    INDEX
    Explanations

    command prompt interactions

    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
     After
    -1.66
     Needless
    -1.50
     even
    -1.45
     venerdì
    -1.43
    鴣
    -1.40
    pravy
    -1.38
     but
    -1.38
    After
    -1.37
    ٴ
    -1.37
     –
    -1.36
    POSITIVE LOGITS
     \&
    1.71
    \&
    1.53
    菹
    1.50
     deaktivi
    1.49
    vaila
    1.46
     inspirasi
    1.46
    IZACIÓN
    1.45
    cepted
    1.42
    -...
    1.41
     prega
    1.41
    Activations Density 0.003%

    No Known Activations