© 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-65K
    7. 51253
    Prev
    Next
    INDEX
    Explanations

    rendering lists and components

    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_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
    בר
    0.44
     αντα
    0.43
     Innovation
    0.39
    Innovation
    0.38
     ब्र
    0.37
    蠟
    0.37
     +\
    0.37
    जाम
    0.36
     ""<
    0.35
    ებას
    0.35
    POSITIVE LOGITS
     conditionally
    0.39
    情的
    0.39
    注释
    0.37
    TypeError
    0.37
     TypeError
    0.37
    あくまで
    0.36
    iniert
    0.36
    REQUIRED
    0.36
    iertos
    0.36
    ignore
    0.36
    Activations Density 0.002%

    No Known Activations