© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44139
    Prev
    Next
    INDEX
    Explanations

    JavaScript code snippets

    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
    ↵
    -1.77
     Banyak
    -1.38
    %).
    -1.30
     będzie
    -1.30
    レベル
    -1.23
     vacanze
    -1.23
    cknow
    -1.20
    quées
    -1.19
    focused
    -1.18
     jednom
    -1.18
    POSITIVE LOGITS
     with
    2.03
     of
    1.65
     and
    1.53
    </h2>
    1.46
    </em>
    1.43
     also
    1.43
    ォ
    1.37
    )
    1.36
     이해
    1.36
    牴
    1.33
    Activations Density 0.017%

    No Known Activations