© 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. 188494
    Prev
    Next
    INDEX
    Explanations

    describes states or roles

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

    steam, cognitive, email, grandfather, sprint, wanting

    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
    IE
    0.56
     dre
    0.49
     Tribe
    0.49
     i
    0.48
     pupil
    0.48
     reared
    0.47
     scintill
    0.46
     TNF
    0.46
     fisi
    0.46
     mie
    0.45
    POSITIVE LOGITS
    齙
    0.49
    adeso
    0.47
     centaines
    0.45
    employ
    0.44
    antaranya
    0.44
    salir
    0.44
    tempat
    0.43
     изго
    0.43
    ੈਂ
    0.43
    iddel
    0.42
    Activations Density 0.000%

    No Known Activations