© 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. 2267
    Prev
    Next
    INDEX
    Explanations

    mailing and outputting

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

    formula, lengthwise, mental, eyes, double, wild, order, service, unassigned

    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
     group
    0.60
     bank
    0.57
     men
    0.54
     ki
    0.54
     s
    0.53
     ratio
    0.53
     director
    0.52
     law
    0.52
     representative
    0.52
     rat
    0.51
    POSITIVE LOGITS
     mesmas
    0.55
     másc
    0.53
    нова
    0.50
    વ
    0.49
     ВС
    0.49
     outras
    0.48
     pavatt
    0.48
     cognitiva
    0.48
    猞
    0.48
     instância
    0.48
    Activations Density 0.000%

    No Known Activations