© 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. 31004
    Prev
    Next
    INDEX
    Explanations

    novel, understand, hunt, fill, saving, sampling, action, future

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

    core principles and command

    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
     fascist
    0.49
    اج
    0.48
     restroom
    0.47
    )
    0.47
     extremist
    0.46
    etos
    0.45
    ╦
    0.45
    тные
    0.44
     seller
    0.44
     biker
    0.44
    POSITIVE LOGITS
    Oste
    0.50
     गामा
    0.49
    össä
    0.49
     പിന്തുണ
    0.48
    <unused236>
    0.47
    pte
    0.47
     Oste
    0.47
    ED
    0.46
     रविवार
    0.46
     chcia
    0.46
    Activations Density 0.000%

    No Known Activations