© 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. 66131
    Prev
    Next
    INDEX
    Explanations

    reporting prize being awarded

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

    social movements and culture

    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
    ্লীল
    0.43
    роятно
    0.41
     officer
    0.40
     '".$
    0.40
     dlatego
    0.40
    wohl
    0.39
     것이
    0.38
    iters
    0.38
    ަލ
    0.38
    ie
    0.38
    POSITIVE LOGITS
    ሳይ
    0.51
     revenues
    0.48
    แรก
    0.48
    ⁶
    0.47
     präsentiert
    0.46
    亮相
    0.46
    सेप्शन
    0.44
     coffers
    0.44
    raphene
    0.44
     выступления
    0.44
    Activations Density 0.001%

    No Known Activations