© 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. 219370
    Prev
    Next
    INDEX
    Explanations

    grand questions, shame, ratio, Country

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

    sometimes playful

    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
    력이
    0.49
    가
    0.49
    說
    0.47
    彼は
    0.47
    ने
    0.46
    കോ
    0.46
    欢迎
    0.46
    რო
    0.45
    زار
    0.45
     neurology
    0.44
    POSITIVE LOGITS
    jr
    0.49
     किन्तु
    0.48
    Lr
    0.48
    UM
    0.47
    Issledovatel
    0.47
    endig
    0.46
     প্রশ
    0.45
    enio
    0.45
     EV
    0.45
     episod
    0.45
    Activations Density 0.000%

    No Known Activations