© 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. 105714
    Prev
    Next
    INDEX
    Explanations

    formal assessments and evaluations

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

    mom father Liberty Live

    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
     Mohammad
    0.48
     மையம்
    0.48
    ార
    0.48
    )~
    0.46
     кеңсеси
    0.46
    නික
    0.46
    }~\
    0.46
    ozz
    0.45
     Lank
    0.45
     خارجی
    0.44
    POSITIVE LOGITS
    Trial
    0.45
     muertos
    0.43
     rozmi
    0.42
     monstros
    0.42
    鐗
    0.42
     giorno
    0.42
    طه
    0.42
    pla
    0.41
    ﻭ
    0.41
    कोट
    0.41
    Activations Density 0.000%

    No Known Activations