© 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. 168273
    Prev
    Next
    INDEX
    Explanations

    Regular Expressions, DevOps, Events

    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
     oxidizing
    0.43
     pissed
    0.41
    尸
    0.38
     marching
    0.37
     patrolling
    0.37
    व्ह
    0.36
     moo
    0.36
     mustered
    0.36
    şi
    0.35
     importing
    0.35
    POSITIVE LOGITS
     subsystem
    0.43
    internalType
    0.43
     Bits
    0.43
     रीजन
    0.42
    ➌
    0.41
    เหนือ
    0.40
     কৌশল
    0.40
     czynności
    0.38
    Bits
    0.38
     Methodist
    0.37
    Activations Density 0.000%

    No Known Activations