© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5542
    Prev
    Next
    INDEX
    Explanations

    solved

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

    solves, solving, solved

    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_53_width_65k_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
     [`
    0.43
     marav
    0.38
    얏
    0.38
     (`
    0.38
     Referential
    0.37
     !}\
    0.37
    )->
    0.36
    ੌ
    0.36
    κρα
    0.36
     Hands
    0.35
    POSITIVE LOGITS
    vable
    0.63
    ving
    0.60
     sol
    0.55
     Sol
    0.49
    ves
    0.47
    ved
    0.47
    ihull
    0.46
    VING
    0.45
    iving
    0.45
    ソル
    0.44
    Activations Density 0.000%

    No Known Activations