© 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. 160589
    Prev
    Next
    INDEX
    Explanations

    personal liability

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

    vector direction, magnitude

    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
    ウ
    0.57
    予
    0.47
    িস্থ
    0.47
     terse
    0.46
     Cott
    0.44
    联
    0.44
    ประ
    0.44
     pressur
    0.43
    𝗖
    0.43
    Р
    0.42
    POSITIVE LOGITS
     اعتبار
    0.47
    isation
    0.44
    ostino
    0.44
    InOut
    0.44
    ar
    0.43
    ogeneity
    0.43
     tekint
    0.42
     جذ
    0.41
     dinam
    0.41
    ět
    0.41
    Activations Density 0.001%

    No Known Activations