© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1673
    Prev
    Next
    INDEX
    Explanations

    time of day until sunset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دام
    0.49
    بھ
    0.46
    サロン
    0.45
    和其他
    0.45
     outflow
    0.44
     আনন্দে
    0.44
    ﻢ
    0.44
     ډاونلوډ
    0.43
    量
    0.43
     resuelve
    0.43
    POSITIVE LOGITS
    ੰ
    0.43
    der
    0.42
    見
    0.41
    :],
    0.41
    ℡
    0.40
    telefon
    0.39
    мі
    0.38
     काही
    0.38
    फना
    0.38
    fgets
    0.38
    Activations Density 0.000%

    No Known Activations