© 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. 186024
    Prev
    Next
    INDEX
    Explanations

    quote attribution

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

    harmful relationship requests

    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
    тивных
    0.51
     redundant
    0.48
    螻
    0.48
     introns
    0.47
    тивной
    0.46
    밌
    0.44
    只需
    0.44
    कार्बन
    0.43
    穗
    0.43
     mathcolor
    0.42
    POSITIVE LOGITS
     écart
    0.49
     enjeux
    0.47
     luj
    0.46
    ott
    0.46
     alrededor
    0.44
     invigor
    0.44
     opportun
    0.44
     ajustes
    0.42
    сл
    0.41
     καὶ
    0.41
    Activations Density 0.000%

    No Known Activations