© 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. 58276
    Prev
    Next
    INDEX
    Explanations

    account, goal, security, woman, alternatives, arrest, control, running

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

    purpose clauses or technical specifications

    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
    ッキリ
    0.50
    ellingen
    0.46
    сля
    0.45
    कैसे
    0.45
    榈
    0.45
     alumnos
    0.45
    ংকের
    0.44
    ğe
    0.44
    ံ
    0.44
    JComboBox
    0.44
    POSITIVE LOGITS
     因
    0.54
     注意
    0.50
     此
    0.50
     因为
    0.49
     •
    0.48
     处理
    0.46
     reorganized
    0.45
     对
    0.44
    పథ
    0.44
     相关
    0.44
    Activations Density 0.000%

    No Known Activations