© 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. 203462
    Prev
    Next
    INDEX
    Explanations

    light, lighting, lit, lighted

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

    haunted house, appraiser, detonated

    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
     ਕਿਸ
    0.46
     pesce
    0.45
    R
    0.45
     pesc
    0.44
     reckoning
    0.44
    mata
    0.44
     pol
    0.43
     aiming
    0.42
    TS
    0.41
    MID
    0.41
    POSITIVE LOGITS
    毂
    0.50
    篑
    0.47
    󠁴
    0.46
    Luego
    0.46
     большо
    0.46
     сезоне
    0.45
     tràn
    0.45
     умолчанию
    0.44
     зал
    0.43
     часу
    0.43
    Activations Density 0.015%

    No Known Activations