© 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. 246178
    Prev
    Next
    INDEX
    Explanations

    visual input, final act, avid camper, proposed amendment

    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
     Tyl
    0.44
    褙
    0.42
    theme
    0.41
     sols
    0.40
    唪
    0.40
    飲料
    0.39
     измене
    0.39
    -¹
    0.38
     registers
    0.38
     stents
    0.38
    POSITIVE LOGITS
    ﻫ
    0.54
    𝗈
    0.54
     متابعي
    0.52
     pareja
    0.51
     ។
    0.51
     हेव
    0.50
    érc
    0.50
    च्चय
    0.50
     tarea
    0.49
     decidió
    0.48
    Activations Density 0.000%

    No Known Activations