© 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. 67398
    Prev
    Next
    INDEX
    Explanations

    notify, protect, email, clipboard

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

    weather and destination discussions

    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
     রই
    0.51
    ֵ
    0.50
    Myst
    0.46
    𝓇
    0.46
    Danger
    0.46
     кап
    0.46
    ловой
    0.44
     INTEREST
    0.44
    拿起
    0.44
    பிர
    0.43
    POSITIVE LOGITS
    udsman
    0.52
     وي
    0.44
    abilir
    0.44
    ビ
    0.42
     ビ
    0.42
    arsen
    0.41
     recort
    0.41
     आराम
    0.40
    sman
    0.40
     incrementally
    0.40
    Activations Density 0.000%

    No Known Activations