© 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. 103954
    Prev
    Next
    INDEX
    Explanations

    server hosts

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

    offer support

    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
    тари
    0.52
    톄
    0.50
    墳
    0.49
    진다
    0.49
    닉
    0.49
    사회
    0.48
    ازی
    0.47
    名の
    0.47
    呂
    0.46
    種類の
    0.46
    POSITIVE LOGITS
    ours
    0.47
    zech
    0.46
    am
    0.45
    oury
    0.45
    ida
    0.44
    r
    0.44
    illa
    0.43
    ab
    0.42
    CUR
    0.42
    usal
    0.42
    Activations Density 0.000%

    No Known Activations