© 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-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3652
    Prev
    Next
    INDEX
    Explanations

    qualified as COM, Direct, Electric

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    7
    1.39
     клас
    1.38
    rinsic
    1.30
     nasc
    1.29
    6
    1.27
    Ck
    1.26
    ksen
    1.26
    ubis
    1.26
    5
    1.22
    8
    1.22
    POSITIVE LOGITS
     arrows
    1.21
     tables
    1.20
     adapter
    1.17
     favourites
    1.11
     timetable
    1.11
     illustrator
    1.10
     erythro
    1.07
     illustrations
    1.05
     arrang
    1.05
     optomet
    1.04
    Activations Density 0.185%

    No Known Activations