© 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. 4428
    Prev
    Next
    INDEX
    Explanations

    foreign words German descriptions

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

    groups and specific roles

    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
    .\
    0.37
    .<
    0.35
    СТ
    0.34
    }
    0.34
    ﾝ
    0.33
     pedibusque
    0.31
    Studies
    0.31
    ஸ்
    0.31
    Graph
    0.31
    X
    0.31
    POSITIVE LOGITS
     policing
    0.49
     thugs
    0.44
     gangsters
    0.43
     mercenaries
    0.42
     servicemen
    0.42
     policemen
    0.40
     harassing
    0.40
     unscrupulous
    0.40
     ktorí
    0.40
     propaganda
    0.39
    Activations Density 0.000%

    No Known Activations