© 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. 71814
    Prev
    Next
    INDEX
    Explanations

    Q followed by question tokens

    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
     and
    -2.45
    XXIII
    -2.13
    xvii
    -2.06
    &
    -2.00
    "-"
    -1.99
    🗿
    -1.99
    🏅
    -1.98
     artikelen
    -1.96
    .'-
    -1.94
     exclusivamente
    -1.93
    POSITIVE LOGITS
     your
    2.08
    4
    2.02
    也许
    1.96
    no
    1.95
    3
    1.92
    甚至
    1.92
    或者
    1.88
    或
    1.85
    1
    1.85
    AL
    1.80
    Activations Density 0.000%

    No Known Activations