© 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. 181259
    Prev
    Next
    INDEX
    Explanations

    submitting entry

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

    trading strategy

    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
    imizi
    0.49
    니어
    0.47
    脱毛
    0.44
    ัด
    0.44
     tomon
    0.43
    ご覧
    0.42
    奶奶
    0.40
    挫
    0.40
    ራስ
    0.39
    urando
    0.39
    POSITIVE LOGITS
     Poet
    0.50
    خ
    0.49
     forum
    0.48
     Forum
    0.48
    forum
    0.47
     Hội
    0.47
     Thermodynamic
    0.46
     symposium
    0.45
     Janus
    0.45
     or
    0.45
    Activations Density 0.001%

    No Known Activations