© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103546
    Prev
    Next
    INDEX
    Explanations

    tens of

    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
    </b>
    -2.84
     Currently
    -2.66
     Keeping
    -2.48
    ");
    -2.48
    pinephrine
    -2.47
     Punkten
    -2.45
    indelijk
    -2.42
     Until
    -2.42
     Contrary
    -2.41
     When
    -2.39
    POSITIVE LOGITS
    </strong>
    3.59
    al
    3.55
    </h3>
    3.48
    ꜆
    3.09
    檍
    2.95
    镲
    2.88
    and
    2.86
    </em>
    2.72
    蠖
    2.72
    鶫
    2.69
    Activations Density 0.005%

    No Known Activations