© 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. 182327
    Prev
    Next
    INDEX
    Explanations

    cheers, :)

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

    safety, social, term

    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
    อม
    0.49
    ティア
    0.47
    澹
    0.47
    ᄍ
    0.46
    αιν
    0.46
    ającego
    0.45
     {}>,
    0.45
    ังก
    0.44
    ัญลักษณ์
    0.44
    ड़ने
    0.43
    POSITIVE LOGITS
     භ
    0.48
    vér
    0.48
     в
    0.47
     други
    0.46
     архив
    0.46
     активи
    0.46
    ,*
    0.45
    lies
    0.45
     др
    0.45
    executed
    0.45
    Activations Density 0.000%

    No Known Activations