© 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. 60922
    Prev
    Next
    INDEX
    Explanations

    sequences ending in, like

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

    review of, if you

    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
     destiny
    0.45
    ამე
    0.44
    pay
    0.43
    ações
    0.43
     fairytale
    0.43
     d
    0.42
     Roos
    0.42
    лина
    0.41
    дэ
    0.41
    פ
    0.41
    POSITIVE LOGITS
     पढ़
    0.50
     fileprivate
    0.47
     verkl
    0.47
     具体
    0.46
    ৰি
    0.46
    アプリ
    0.46
    RefManager
    0.46
    RZ
    0.45
     وعند
    0.45
    CAC
    0.45
    Activations Density 0.000%

    No Known Activations