© 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. 150349
    Prev
    Next
    INDEX
    Explanations

    price, pack, titles, failure

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

    greetings and specific topics

    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
    調
    0.52
     weten
    0.43
     její
    0.43
     wheels
    0.42
    消毒
    0.41
     zoveel
    0.41
     isKindOfClass
    0.41
    <unused96>
    0.41
    াৎ
    0.41
     άλλ
    0.41
    POSITIVE LOGITS
     Lore
    0.53
    LQ
    0.50
    ומר
    0.50
    悱
    0.47
     Tarot
    0.47
    㑼
    0.46
     Loren
    0.45
    RecordPtr
    0.45
    THANK
    0.45
    issen
    0.44
    Activations Density 0.000%

    No Known Activations