© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 135918
    Prev
    Next
    INDEX
    Explanations

    section markers like ** or *

    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
    酺
    0.38
    ठमाडौं
    0.38
    टाम
    0.36
     beck
    0.36
     ايش
    0.35
    స్తు
    0.35
    ưở
    0.35
     đấy
    0.35
    誒
    0.34
    வல
    0.34
    POSITIVE LOGITS
     graduated
    0.44
    agnetic
    0.39
    redients
    0.39
     threading
    0.38
     outlets
    0.37
     Apre
    0.37
     meilleures
    0.36
     prevention
    0.36
     passive
    0.36
     Πε
    0.36
    Activations Density 0.000%

    No Known Activations