© 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. 87858
    Prev
    Next
    INDEX
    Explanations

    years or

    np_acts-logits-general · gemini-2.5-flash-lite

    ability to help with tasks

    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
     காமெடி
    0.60
    忑
    0.57
     iccad
    0.54
    ក្ត
    0.54
     思う
    0.53
    觑
    0.53
    HasStarred
    0.52
    ഽ
    0.52
    ഗ്യ
    0.52
     لیں
    0.50
    POSITIVE LOGITS
    MO
    0.64
    b
    0.57
    RO
    0.56
     at
    0.55
     and
    0.55
    f
    0.55
    <0x0D>
    0.54
     MO
    0.54
     registration
    0.54
    ark
    0.53
    Activations Density 0.001%

    No Known Activations