© 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. 113316
    Prev
    Next
    INDEX
    Explanations

    http, ., ,

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

    foreign languages and words

    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
    Behaviour
    0.49
    掲載
    0.48
    
    0.47
    餉
    0.47
    生
    0.47
    蝿
    0.47
    ரி
    0.46
    ուս
    0.46
    Cours
    0.46
    Position
    0.46
    POSITIVE LOGITS
     znovu
    0.51
    </b>
    0.49
     จริง
    0.47
     madera
    0.47
     আবারো
    0.47
     popped
    0.46
    ugawa
    0.45
     zum
    0.44
     jordan
    0.44
     dř
    0.44
    Activations Density 0.000%

    No Known Activations