© 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. 61151
    Prev
    Next
    INDEX
    Explanations

    platforms and commands

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

    Pearson correlation, financial growth, programming constructs

    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
     Stelle
    0.47
     Trending
    0.46
     Scream
    0.46
    橛
    0.46
     killings
    0.45
     solicited
    0.45
     Shasta
    0.45
    犀
    0.45
    缺
    0.44
    其他
    0.44
    POSITIVE LOGITS
     Информация
    0.51
    rmi
    0.50
    Cola
    0.50
    Информация
    0.49
    on
    0.48
    форми
    0.47
    compressed
    0.47
    songwriter
    0.46
    واری
    0.46
    information
    0.46
    Activations Density 0.000%

    No Known Activations