© 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. 67848
    Prev
    Next
    INDEX
    Explanations

    a/an + descriptive word

    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
     and
    -3.55
     all
    -2.28
     or
    -2.20
    ("
    -2.09
    🌸
    -1.98
     these
    -1.98
     with
    -1.92
     those
    -1.91
    ⁡
    -1.88
    🌻
    -1.88
    POSITIVE LOGITS
    乄
    2.19
    horloge
    2.11
     distanza
    2.02
     dreary
    2.02
     BECAUSE
    1.98
    蚨
    1.97
    噥
    1.97
     diventa
    1.96
    attente
    1.95
     jednej
    1.93
    Activations Density 0.015%

    No Known Activations