© 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. 148064
    Prev
    Next
    INDEX
    Explanations

    locations and specific entities

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

    dark secrets or inventory data

    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
    ંમે
    0.53
     activate
    0.52
     precipitate
    0.50
     puls
    0.50
     compensate
    0.48
    萵
    0.47
    ार्
    0.47
    GN
    0.46
    姍
    0.46
     facilitate
    0.45
    POSITIVE LOGITS
    sym
    0.54
    скае
    0.53
     Takahashi
    0.51
     Tengo
    0.50
     Schwier
    0.50
    resol
    0.50
     tengo
    0.48
     QuantityOnHand
    0.48
    Resolution
    0.48
     অসম্ভব
    0.48
    Activations Density 0.000%

    No Known Activations