© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 31276
    Prev
    Next
    INDEX
    Explanations

    ASA on PC

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

    foreign words and phrases

    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
     ball
    0.47
    ).
    0.44
     situations
    0.44
     Ball
    0.44
     question
    0.44
     catalog
    0.44
     amounted
    0.42
    -
    0.42
     boiled
    0.41
    ↵↵
    0.40
    POSITIVE LOGITS
    řízení
    0.54
    镌
    0.48
     DENUMIRE
    0.46
     zejména
    0.46
     Бушлай
    0.45
     анд
    0.44
    xcodep
    0.43
     aisément
    0.43
     zaměst
    0.42
     emisiones
    0.42
    Activations Density 0.000%

    No Known Activations