© 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. 31-GEMMASCOPE-2-RES-262K
    7. 21497
    Prev
    Next
    INDEX
    Explanations

    identity and exposure

    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_31_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
     …
    0.41
     tremble
    0.41
    ynch
    0.39
    ˂
    0.39
     violently
    0.38
     overwhelming
    0.37
    anging
    0.37
    trem
    0.37
     escalate
    0.36
     convuls
    0.36
    POSITIVE LOGITS
     yazı
    0.45
     Dining
    0.44
    燔
    0.43
     売場面積
    0.42
     việc
    0.42
     संपाद
    0.42
    摒
    0.41
     Accommodation
    0.41
    邂
    0.41
     घोड़
    0.41
    Activations Density 0.001%

    No Known Activations