© 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. 84409
    Prev
    Next
    INDEX
    Explanations

    programming code elements

    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
    _
    -3.06
    a
    -3.05
    .
    -3.02
    6
    -2.73
    <
    -2.64
    8
    -2.64
    On
    -2.61
    In
    -2.61
    7
    -2.58
    }
    -2.55
    POSITIVE LOGITS
    ﮕ
    2.61
    GEBUR
    2.45
    ￬
    2.41
    koszulka
    2.31
     potes
    2.31
    bluza
    2.31
    ῞
    2.28
    聃
    2.27
     maît
    2.27
    ſſen
    2.27
    Activations Density 0.000%

    No Known Activations