© 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. 57792
    Prev
    Next
    INDEX
    Explanations

    acceptance and agreement

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

    acceptance indicating consensus

    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
    ণ্ঠে
    0.55
     กราบ
    0.52
    ini
    0.50
    info
    0.48
    astotal
    0.48
    id
    0.46
    '].
    0.45
    พูด
    0.45
     వచ్చే
    0.43
    in
    0.43
    POSITIVE LOGITS
    She
    0.42
     황
    0.42
    騾
    0.41
     She
    0.40
     라이
    0.40
    마다
    0.39
    ברה
    0.39
     Biblioteca
    0.39
     Micron
    0.38
    VIDIA
    0.38
    Activations Density 0.001%

    No Known Activations