© 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. 181677
    Prev
    Next
    INDEX
    Explanations

    introduction or description

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

    surprisingly, sacrificing, portion, complex, policy

    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
     subpar
    0.52
    engineered
    0.52
     embossed
    0.51
    bal
    0.49
    EEG
    0.48
    SVG
    0.47
    س
    0.46
    params
    0.46
    Pipeline
    0.46
     muffin
    0.46
    POSITIVE LOGITS
    żliw
    0.46
     없는
    0.44
     Jews
    0.43
    ଥ
    0.42
     없습니다
    0.42
    жий
    0.42
     दुस
    0.41
     아닌
    0.40
     없어
    0.39
     листо
    0.39
    Activations Density 0.000%

    No Known Activations