© 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. 18163
    Prev
    Next
    INDEX
    Explanations

    location or state

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

    ingredients and instructions

    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
    hitth
    0.31
    piej
    0.29
    ccncc
    0.29
    acchati
    0.28
    舂
    0.28
     connaissance
    0.28
    assaytype
    0.28
    ಿಗೆ
    0.27
    ukiyoe
    0.27
    ]]->
    0.27
    POSITIVE LOGITS
     resided
    0.31
     reside
    0.29
     unsurprisingly
    0.29
    S
    0.28
     квартира
    0.28
    K
    0.28
     squarely
    0.27
    to
    0.27
     headquartered
    0.27
    Ф
    0.26
    Activations Density 0.000%

    No Known Activations