© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1618
    Prev
    Next
    INDEX
    Explanations

    conditional impact on requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mision
    0.57
    ด
    0.53
    Ward
    0.51
    尟
    0.51
    Mission
    0.50
    ༔
    0.50
    诨
    0.49
     MISSION
    0.49
    mission
    0.49
    蕌
    0.48
    POSITIVE LOGITS
    ak
    0.49
     P
    0.48
    S
    0.47
    anedi
    0.43
    drops
    0.42
     Chong
    0.42
     П
    0.41
    P
    0.41
     Π
    0.41
    ৰি
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.