© 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. 120645
    Prev
    Next
    INDEX
    Explanations

    course, workout, place, fingertips, ability, fully, typically

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

    relationships and alliances

    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
     preoccupied
    0.46
    сну
    0.45
    теше
    0.44
     derived
    0.43
     susceptible
    0.43
     Сан
    0.42
     সহকারী
    0.42
    œ
    0.42
    лых
    0.41
     suspended
    0.41
    POSITIVE LOGITS
     Bewertung
    0.50
    Unter
    0.49
     hintergrund
    0.49
     Portugal
    0.47
     Beweg
    0.47
     Regulator
    0.45
    OG
    0.44
    }-\
    0.44
     erste
    0.44
     Kopf
    0.44
    Activations Density 0.001%

    No Known Activations