© 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. 186076
    Prev
    Next
    INDEX
    Explanations

    great moments, creative accounting, packaging materials

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

    Internet Connection, Energy Dependent

    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
    мар
    0.47
    ט
    0.46
    ейчас
    0.44
    खाने
    0.44
     absor
    0.44
    <unused2127>
    0.43
     გარ
    0.43
    restaurant
    0.43
    ｔ
    0.43
    voll
    0.42
    POSITIVE LOGITS
    ْن
    0.45
     Trên
    0.43
    Trên
    0.43
    جموع
    0.42
    Mountains
    0.41
    改めて
    0.41
     patients
    0.40
    Interfaces
    0.40
     beeh
    0.40
    第一題
    0.40
    Activations Density 0.000%

    No Known Activations