© 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. 204024
    Prev
    Next
    INDEX
    Explanations

    specific abstract concepts

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

    abstract scene descriptions

    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
     సమస్య
    0.46
    MktCap
    0.46
    ЕТ
    0.45
    ্যান্ড
    0.44
     разделе
    0.44
    dyž
    0.44
    iesen
    0.43
    㖅
    0.43
    рави
    0.43
     социа
    0.43
    POSITIVE LOGITS
    D
    0.50
    Un
    0.49
    Far
    0.48
    Forty
    0.47
     Far
    0.46
     Un
    0.44
    H
    0.44
    _,
    0.43
    Full
    0.42
     D
    0.42
    Activations Density 0.002%

    No Known Activations