© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167918
    Prev
    Next
    INDEX
    Explanations

    Identifying directors and writers

    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
    侩
    0.47
    เอียด
    0.45
     unbear
    0.44
    ʳ
    0.44
     अभियंता
    0.44
    𝓾
    0.44
    嬷
    0.44
     trener
    0.44
     அகத்திய
    0.44
     อาจารย์
    0.44
    POSITIVE LOGITS
     writers
    0.48
     co
    0.46
     writing
    0.44
     based
    0.42
     Writers
    0.42
     newcomers
    0.42
     wrote
    0.41
     writer
    0.40
     W
    0.40
     performed
    0.40
    Activations Density 0.002%

    No Known Activations