© 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. 59327
    Prev
    Next
    INDEX
    Explanations

    business and planning

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

    perspective and societal elements

    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
     அடிப்பட
    0.44
    这一切
    0.44
     począ
    0.43
    翕
    0.41
     enquiries
    0.41
     brows
    0.40
    első
    0.40
    辅
    0.39
    æld
    0.39
     Adirond
    0.39
    POSITIVE LOGITS
    viendo
    0.48
    輸出
    0.45
    कारात्मक
    0.45
     humiliation
    0.44
     хотим
    0.44
    部に
    0.43
     塩
    0.42
     manure
    0.42
    でお
    0.42
     polluting
    0.41
    Activations Density 0.000%

    No Known Activations