© 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. 90375
    Prev
    Next
    INDEX
    Explanations

    non-latin scripts

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

    saying how to do something

    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
    したが
    0.52
     Ignore
    0.52
     Θε
    0.48
     GIRL
    0.47
     η
    0.47
     গতি
    0.47
     proportionately
    0.46
     Eucharist
    0.46
     θε
    0.45
    屼
    0.44
    POSITIVE LOGITS
    ضر
    0.45
    ुर
    0.45
    स्टी
    0.45
    ПА
    0.45
    пере
    0.44
    ামাক
    0.43
    वाट
    0.43
    вет
    0.42
     শিল
    0.42
    gaver
    0.42
    Activations Density 0.000%

    No Known Activations