© 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. 151602
    Prev
    Next
    INDEX
    Explanations

    time of day

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

    damaging effect and unpleasantness

    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
     Depreciation
    0.58
    殁
    0.50
     छोटा
    0.49
    ្នក
    0.48
    手法
    0.48
    奔驰
    0.47
    浐
    0.47
    之为
    0.46
     हत्याकांड
    0.46
    萤
    0.46
    POSITIVE LOGITS
    processed
    0.50
    pulse
    0.48
     beasts
    0.47
     with
    0.45
     cael
    0.44
    .³
    0.43
     animals
    0.43
    splitter
    0.43
     rendered
    0.42
     chewing
    0.42
    Activations Density 0.000%

    No Known Activations