© 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. 80106
    Prev
    Next
    INDEX
    Explanations

    known approximation, knows exactly

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

    meaninglessness, absurdity, prolonged duration, system reliability

    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
     Allows
    0.60
     நாடுகளில்
    0.55
     allows
    0.54
     precludes
    0.54
    𒌇
    0.50
    éments
    0.49
     prohibits
    0.49
     настрой
    0.49
     árboles
    0.48
     когато
    0.48
    POSITIVE LOGITS
    ’
    0.62
    '
    0.50
    ดัง
    0.49
    ิ
    0.47
    Ah
    0.45
    ink
    0.45
    Geb
    0.44
    Bak
    0.44
    0.44
    ы
    0.44
    Activations Density 0.000%

    No Known Activations