© 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. 73068
    Prev
    Next
    INDEX
    Explanations

    not so

    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
    -
    -2.67
     our
    -2.28
    $
    -2.14
     (“
    -2.11
    ”
    -1.97
    ”.
    -1.93
     “
    -1.89
     it
    -1.78
    ,”
    -1.73
    “
    -1.73
    POSITIVE LOGITS
     parlamento
    1.94
     voci
    1.78
    銕
    1.74
     ragioni
    1.69
     peggio
    1.68
     notizie
    1.67
     istruzioni
    1.66
     lezioni
    1.66
     borsa
    1.65
     citazioni
    1.65
    Activations Density 0.027%

    No Known Activations