© 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. 163756
    Prev
    Next
    INDEX
    Explanations

    sequence predictor

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

    numbers and mathematical concepts

    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
    원
    0.51
    ক
    0.50
    ў
    0.50
    뜻
    0.49
    주의
    0.47
     aviso
    0.46
    ћи
    0.45
    व
    0.45
    失
    0.45
     Loss
    0.45
    POSITIVE LOGITS
    ying
    0.50
     удосто
    0.50
    yr
    0.48
    ancell
    0.44
    olutions
    0.44
    yan
    0.44
    urrection
    0.43
     μεταξύ
    0.43
    gorod
    0.43
    eby
    0.42
    Activations Density 0.000%

    No Known Activations