© 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. 154617
    Prev
    Next
    INDEX
    Explanations

    surprise her, regarding this, certified free

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

    explicitly stating

    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
     እን
    0.54
     இவை
    0.51
     ছাড়
    0.50
    createSprite
    0.50
     spriteBatch
    0.49
    𒋫
    0.49
    localVarPath
    0.49
     சென்ன
    0.48
     GoObject
    0.47
     பழைய
    0.47
    POSITIVE LOGITS
    E
    0.54
    EL
    0.52
    0.52
    EV
    0.52
    I
    0.49
    EH
    0.47
    LL
    0.47
     penis
    0.47
    HE
    0.44
     RNG
    0.44
    Activations Density 0.002%

    No Known Activations