© 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. 111656
    Prev
    Next
    INDEX
    Explanations

    injuries, site, determination

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

    dust motes in light

    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
    ธาร
    0.52
    PERSON
    0.51
    文字列
    0.51
    ِين
    0.49
     академи
    0.48
    ┕
    0.48
    淑
    0.47
    簷
    0.47
    ◽
    0.47
    colnames
    0.46
    POSITIVE LOGITS
    i
    0.57
     muy
    0.47
    ovanie
    0.46
    avaş
    0.46
     pray
    0.46
    އ
    0.45
    er
    0.45
    ową
    0.45
     muito
    0.44
     ambiente
    0.44
    Activations Density 0.000%

    No Known Activations