© 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. 216865
    Prev
    Next
    INDEX
    Explanations

    search term

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

    key objects

    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
    ி
    0.48
    ي
    0.43
     рэгістра
    0.42
    vout
    0.41
     meiner
    0.41
    i
    0.41
    variant
    0.41
    ì
    0.41
     geweest
    0.40
    oth
    0.40
    POSITIVE LOGITS
     forearm
    0.50
     gastroenter
    0.47
     automobiles
    0.45
    ಟರ್
    0.45
     rollerskates
    0.44
     racetrack
    0.44
     çevre
    0.44
     mencegah
    0.43
     fece
    0.43
     trache
    0.43
    Activations Density 0.002%

    No Known Activations