© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 202520
    Prev
    Next
    INDEX
    Explanations

    creative and artistic

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

    abstract concepts or states

    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
     набор
    0.50
    としている
    0.49
     ರೂಪ
    0.46
     дан
    0.46
     опор
    0.46
    今回
    0.45
     ឬ
    0.45
    吞
    0.45
    ęp
    0.45
     datasets
    0.44
    POSITIVE LOGITS
    creative
    0.55
    pit
    0.53
    Creative
    0.51
    park
    0.51
     creative
    0.48
    sex
    0.47
     creativo
    0.46
     Creative
    0.46
     medal
    0.45
    studio
    0.44
    Activations Density 0.000%

    No Known Activations