© 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. 201935
    Prev
    Next
    INDEX
    Explanations

    more likely

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

    structuring lists and advice

    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
     ఎదు
    0.50
     представления
    0.48
     pravi
    0.48
     Timurtaş
    0.48
    <unused1072>
    0.47
     postérieures
    0.47
     udě
    0.47
     erbjud
    0.46
     পত
    0.46
     pérd
    0.45
    POSITIVE LOGITS
     OFF
    0.46
    ､
    0.46
     ketone
    0.46
     fetish
    0.46
     capsule
    0.45
     assortment
    0.45
     array
    0.44
     stun
    0.44
    ξ
    0.44
    ARRAY
    0.44
    Activations Density 0.001%

    No Known Activations