© 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. 132051
    Prev
    Next
    INDEX
    Explanations

    dreamy, art, classical, games

    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
    恻
    0.44
    ponent
    0.39
    纽
    0.39
     Tuj
    0.38
    ಾಸ
    0.38
     Indicates
    0.37
     درج
    0.37
    ^(-
    0.37
    ENEMY
    0.37
    表明
    0.37
    POSITIVE LOGITS
     Бого
    0.45
    ঢাকার
    0.41
     springfox
    0.36
     payers
    0.36
     nonconvex
    0.36
    ุงเทพ
    0.35
    ondon
    0.35
    禕
    0.35
    databind
    0.35
     influencers
    0.35
    Activations Density 0.000%

    No Known Activations