© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 87863
    Prev
    Next
    INDEX
    Explanations

    reduce to

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

    actions, states, and potential outcomes

    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
    ziff
    0.48
     लीजिएगा
    0.47
     generously
    0.47
    popularity
    0.47
     এলাকা
    0.46
     popularity
    0.46
     জনপ্রিয়তা
    0.45
    掳
    0.45
     المحلي
    0.44
    essional
    0.44
    POSITIVE LOGITS
     Katherine
    0.42
     Parts
    0.38
     Factories
    0.38
     Inte
    0.37
    MOD
    0.37
     Katrina
    0.37
    ம்பி
    0.37
    can
    0.36
     Tige
    0.36
    끊
    0.36
    Activations Density 0.000%

    No Known Activations