© 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. 243548
    Prev
    Next
    INDEX
    Explanations

    pointless slaughter

    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
    ا
    0.59
    )
    0.56
    าส
    0.54
    ევს
    0.52
    ா
    0.50
     expectancy
    0.48
    жи
    0.48
    嗟
    0.47
     oso
    0.46
    تر
    0.46
    POSITIVE LOGITS
    desktop
    0.47
    matte
    0.44
     Shortly
    0.44
    erné
    0.44
    >//
    0.44
     cột
    0.42
     Matte
    0.42
    ://
    0.42
    nau
    0.42
    mouseleave
    0.41
    Activations Density 0.001%

    No Known Activations