© 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. 72716
    Prev
    Next
    INDEX
    Explanations

    implications for

    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
    </i>
    -2.91
    」，
    -2.77
     It
    -2.70
     With
    -2.58
    </h1>
    -2.53
    皲
    -2.52
     The
    -2.48
     économie
    -2.45
    derdag
    -2.45
    琹
    -2.36
    POSITIVE LOGITS
    0
    3.47
    f
    2.98
    d
    2.78
    ”،
    2.67
    1
    2.61
    </em>
    2.58
    <em>
    2.53
    所以我
    2.50
    5
    2.44
    ing
    2.41
    Activations Density 0.013%

    No Known Activations