© 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. 179565
    Prev
    Next
    INDEX
    Explanations

    delivery disappointment antigen

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

    general protocols

    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
     muqueuse
    0.56
     Bedür
    0.52
    یشہ
    0.50
     puissance
    0.49
    」（
    0.48
    ुरी
    0.47
    廼
    0.47
     패턴
    0.46
    ണ്ടി
    0.46
     ビジネス
    0.46
    POSITIVE LOGITS
    l
    0.58
    d
    0.56
    w
    0.53
    gr
    0.52
    pH
    0.51
    O
    0.47
    trä
    0.46
    rets
    0.46
    riya
    0.46
    gic
    0.46
    Activations Density 0.001%

    No Known Activations