© 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. 15191
    Prev
    Next
    INDEX
    Explanations

    years and events

    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
    翆
    -1.90
     from
    -1.82
     our
    -1.80
    畊
    -1.80
    䴀
    -1.76
    います
    -1.72
     the
    -1.70
    ᱧ
    -1.67
     such
    -1.67
    </em>
    -1.67
    POSITIVE LOGITS
    ↵↵
    2.23
    .
    2.05
    an
    1.99
    f
    1.88
    U
    1.84
    li
    1.80
    j
    1.80
    b
    1.73
     –
    1.72
    —
    1.66
    Activations Density 0.025%

    No Known Activations