© 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. 236657
    Prev
    Next
    INDEX
    Explanations

    central recruitment

    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
     area
    0.59
     in
    0.58
    -
    0.58
     L
    0.56
     S
    0.56
    West
    0.56
    1
    0.56
    ,
    0.54
    M
    0.54
             
    0.52
    POSITIVE LOGITS
    𒇷
    0.66
     sabbam
    0.63
     paralysie
    0.59
     Polaribacter
    0.58
     atthakath
    0.56
     adhipp
    0.55
     मेहनत
    0.54
     húmed
    0.54
    ActionsForRule
    0.53
    ુંદર
    0.53
    Activations Density 0.001%

    No Known Activations