© 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. 53386
    Prev
    Next
    INDEX
    Explanations

    going on, is rude, It’s, was busy, diverse groups, slices to, significance ., fully justified, words to, 6pcs

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

    targeted training

    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
    러스
    0.50
    kelijke
    0.49
    ميل
    0.46
    kelijk
    0.45
    Α
    0.45
     Aplikasi
    0.45
    㘿
    0.45
    بع
    0.44
     अफगानिस्तान
    0.44
     оюндары
    0.43
    POSITIVE LOGITS
     (
    0.53
    ta
    0.53
     are
    0.48
     BLM
    0.48
    top
    0.47
     pressure
    0.47
     rosso
    0.47
     pressures
    0.47
     prostitution
    0.46
     ramping
    0.46
    Activations Density 0.000%

    No Known Activations