© 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. 7256
    Prev
    Next
    INDEX
    Explanations

    access control and limits

    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
     With
    -2.06
    );
    -1.88
    窍
    -1.80
     —
    -1.69
     ONLY
    -1.66
    ctuaries
    -1.63
    astricht
    -1.60
    龔
    -1.59
     because
    -1.59
    )
    -1.55
    POSITIVE LOGITS
    ”،
    2.03
     naszej
    2.00
     récemment
    1.89
    걔
    1.84
    𨭆
    1.83
    Гля
    1.80
     setelan
    1.80
     Это
    1.78
    ⅿ
    1.78
     нашей
    1.75
    Activations Density 0.005%

    No Known Activations