© 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. 41902
    Prev
    Next
    INDEX
    Explanations

    subject to, sent by, worth it, not required

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

    designing, acknowledging, investigating

    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
     крайней
    0.57
    ając
    0.45
    䄸
    0.43
    䅛
    0.42
     শরীরে
    0.41
    cenik
    0.41
    ๒
    0.40
    Ⅱ
    0.39
     সঠিকভাবে
    0.39
    方的
    0.38
    POSITIVE LOGITS
    ?
    0.56
    了不少
    0.54
    いました
    0.52
     jsou
    0.52
    !?
    0.51
    了吧
    0.50
    ってます
    0.50
    了一
    0.49
    രിക്കുന്നു
    0.49
     ayaa
    0.49
    Activations Density 0.223%

    No Known Activations