© 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. 188211
    Prev
    Next
    INDEX
    Explanations

    URLs starting with http

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

    foundation and scope analysis

    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
     r
    0.48
    wl
    0.45
     OG
    0.44
     千
    0.44
    ar
    0.43
     arke
    0.43
     cũng
    0.43
     നല്ല
    0.43
    hh
    0.42
     tudi
    0.42
    POSITIVE LOGITS
    Გ
    0.60
    Ყ
    0.55
     subsets
    0.53
    безпе
    0.53
    Შ
    0.53
    Რ
    0.52
     subroutine
    0.51
    における
    0.50
    適用
    0.49
     implement
    0.49
    Activations Density 0.000%

    No Known Activations