© 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. 190006
    Prev
    Next
    INDEX
    Explanations

    family, sharing, difficult, future

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

    preservation, simple, split, recovery, choices

    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
     Рэ
    0.54
     boardroom
    0.49
    稩
    0.47
     คำ
    0.47
    బో
    0.47
     당신
    0.47
    ทะเล
    0.46
     ਤੁਹਾ
    0.46
     Kowloon
    0.46
    钏
    0.46
    POSITIVE LOGITS
     avantages
    0.50
    wier
    0.49
     appartient
    0.47
    immer
    0.46
     etmek
    0.45
     etmektedir
    0.44
     extrémités
    0.44
     περισσότε
    0.43
    oretically
    0.43
    ين
    0.43
    Activations Density 0.000%

    No Known Activations