© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167661
    Prev
    Next
    INDEX
    Explanations

    course tracking justification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
     Innovation
    0.42
     دور
    0.41
     בק
    0.41
    Innovation
    0.41
    妬
    0.41
    κολ
    0.41
    брав
    0.40
    രാഷ്ട്ര
    0.39
     Ừ
    0.38
     mọi
    0.38
    POSITIVE LOGITS
    เหล่านี้
    0.42
     lush
    0.40
     interracial
    0.40
     mushroom
    0.39
     esses
    0.39
     exuberant
    0.39
    mM
    0.38
    utage
    0.38
     aesthetic
    0.38
     whites
    0.38
    Activations Density 0.001%

    No Known Activations