© 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. 74236
    Prev
    Next
    INDEX
    Explanations

    reading, development, business, media

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

    inflict pain or offer help

    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
     zindagi
    0.51
     tien
    0.48
    </strong>
    0.46
    اٹ
    0.45
     destiny
    0.44
    国立
    0.44
     statistik
    0.44
    다
    0.44
     conquer
    0.44
    ∞
    0.43
    POSITIVE LOGITS
    ডিও
    0.44
     दक्षिणी
    0.43
     peered
    0.43
     температуры
    0.42
    鳗
    0.42
     τρί
    0.42
     оборо
    0.41
     стены
    0.41
    态度
    0.41
    নব
    0.41
    Activations Density 0.002%

    No Known Activations