© 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. 221753
    Prev
    Next
    INDEX
    Explanations

    internet service providers

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

    variables and sequences

    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
    얇
    0.52
    Ꮹ
    0.45
    좋
    0.45
    ཧ
    0.44
    墳
    0.41
     좋
    0.41
    塌
    0.41
    喜歡
    0.41
     것을
    0.40
     좋다
    0.40
    POSITIVE LOGITS
    is
    0.47
    inta
    0.46
    র্ষি
    0.46
    百家乐
    0.45
     Peers
    0.44
     internals
    0.44
     núcle
    0.43
     pecc
    0.42
    ياز
    0.42
    ودي
    0.42
    Activations Density 0.000%

    No Known Activations