© 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. 90529
    Prev
    Next
    INDEX
    Explanations

    over soon

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

    philosophy of technology and absurd descriptions

    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
    ikli
    0.56
    िब
    0.46
    沚
    0.46
    ધાન
    0.45
     Kons
    0.45
    блема
    0.45
     dokument
    0.45
     Dokument
    0.45
     bakteri
    0.45
     Elektron
    0.45
    POSITIVE LOGITS
    AM
    0.53
     perpendicular
    0.49
    CM
    0.47
    ʉ
    0.47
    OM
    0.46
    IND
    0.46
    OB
    0.46
     répart
    0.46
     IND
    0.45
    mm
    0.44
    Activations Density 0.000%

    No Known Activations