© 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. 70272
    Prev
    Next
    INDEX
    Explanations

    late than never

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

    defense or region

    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
    )$
    0.49
     わ
    0.46
    ποιη
    0.46
    ;|
    0.46
    нняя
    0.46
     필
    0.44
    illera
    0.43
    )
    0.43
    /;
    0.43
    ダム
    0.43
    POSITIVE LOGITS
    chik
    0.48
    guj
    0.46
    nelle
    0.45
    guys
    0.45
    spiration
    0.45
    gina
    0.44
     Insta
    0.43
     mochila
    0.43
     auditorium
    0.43
     maniak
    0.42
    Activations Density 0.001%

    No Known Activations