© 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. 159999
    Prev
    Next
    INDEX
    Explanations

    imperial military

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

    code snippets and content

    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
    轢
    0.46
     unlawfully
    0.46
     rocked
    0.46
    渎
    0.46
     구분
    0.45
     punishable
    0.45
     illegally
    0.44
     indented
    0.44
     interfered
    0.44
     ilegal
    0.44
    POSITIVE LOGITS
     pozosta
    0.44
    EL
    0.44
     PROVID
    0.42
     MS
    0.41
    🍎
    0.40
    Remaining
    0.39
    µ
    0.39
    Sequ
    0.39
    OV
    0.39
    AUTHENT
    0.39
    Activations Density 0.001%

    No Known Activations