© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4250
    Prev
    Next
    INDEX
    Explanations

    things that match or fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
     clandestine
    1.73
     dodgy
    1.70
     derel
    1.67
     belated
    1.64
     pust
    1.63
     cowardly
    1.61
    嘤
    1.61
     perilous
    1.61
    悄
    1.61
     murderous
    1.60
    POSITIVE LOGITS
     fit
    2.11
     sesuai
    2.02
     phù
    1.98
     match
    1.96
    fit
    1.95
     fits
    1.90
     suits
    1.89
     suited
    1.88
     suit
    1.88
     matches
    1.87
    Activations Density 0.676%

    No Known Activations