© 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. 138580
    Prev
    Next
    INDEX
    Explanations

    words followed by connectors

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

    general guidelines

    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
     pev
    0.47
     Lazarus
    0.45
     عوام
    0.45
     konc
    0.45
     मनीष
    0.44
    <0xB0>
    0.42
     gep
    0.42
     milliard
    0.40
     cpt
    0.40
     मेन
    0.40
    POSITIVE LOGITS
    웃
    0.49
    스
    0.48
    antwort
    0.47
    吧
    0.47
    人工智能
    0.46
    ハ
    0.46
    好处
    0.46
    ৩৬
    0.46
    বে
    0.45
    参数
    0.45
    Activations Density 0.001%

    No Known Activations