© 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. 84066
    Prev
    Next
    INDEX
    Explanations

    IM or text starting with IM

    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
    A
    -3.41
     Their
    -3.30
    </em>
    -3.27
    "
    -3.22
    It
    -3.14
    2
    -3.08
    K
    -3.03
    </td>
    -3.00
    L
    -2.95
     If
    -2.86
    POSITIVE LOGITS
     ſch
    3.25
    廰
    3.19
    튿
    2.97
    垟
    2.92
    쫑
    2.91
    翃
    2.84
    
    2.75
    ౧
    2.73
     seleccionar
    2.69
    ឣ
    2.67
    Activations Density 0.004%

    No Known Activations