© 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. 95363
    Prev
    Next
    INDEX
    Explanations

    information, requests, registration

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

    environment and sustainability, or specific concepts

    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
     ไ
    0.52
     שה
    0.47
     texture
    0.47
     textural
    0.47
     trận
    0.45
     shaving
    0.45
     kindness
    0.45
     heroin
    0.44
     במ
    0.44
     הת
    0.44
    POSITIVE LOGITS
    к
    0.46
    люс
    0.44
     ज्योति
    0.42
    isiaj
    0.41
     Seite
    0.41
    جميع
    0.41
     Akademii
    0.41
    они
    0.39
    cludes
    0.39
     ismert
    0.39
    Activations Density 0.000%

    No Known Activations