© 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. 5977
    Prev
    Next
    INDEX
    Explanations

    other languages' common words

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

    multilingual content 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
     ump
    0.29
     hapless
    0.28
     speedometer
    0.28
     layoff
    0.26
    0.25
     harrowing
    0.25
     ruck
    0.25
    );
    0.25
     K
    0.25
     \|
    0.25
    POSITIVE LOGITS
     અથવા
    0.36
    زندگی
    0.32
    ில்லியன்
    0.31
     استخدام
    0.30
    Không
    0.30
    Conse
    0.30
     parlare
    0.29
    ࿔
    0.29
    Todas
    0.29
     esperanza
    0.29
    Activations Density 0.054%

    No Known Activations