© 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. 138908
    Prev
    Next
    INDEX
    Explanations

    language features

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

    screaming

    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
     بُ
    0.45
    为什么要
    0.45
    ynucle
    0.45
     وأن
    0.44
    executable
    0.43
    本来
    0.43
    (/(
    0.42
     تنها
    0.42
    单一
    0.42
     오른
    0.42
    POSITIVE LOGITS
    ן
    0.57
     ıs
    0.49
     screamed
    0.46
    ன்
    0.46
     unsurprisingly
    0.43
    ிஸ்த
    0.42
     scream
    0.42
     sürekli
    0.42
     councils
    0.41
     padam
    0.41
    Activations Density 0.000%

    No Known Activations