© 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. 193700
    Prev
    Next
    INDEX
    Explanations

    protocols and metrics

    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
     चिकित्सा
    0.40
     ডাক্ত
    0.38
    هی
    0.38
    ীয়তে
    0.38
    ينه
    0.38
    mnopqrst
    0.37
    抱
    0.37
    utenants
    0.36
    BleStatus
    0.36
     डॉक्टरों
    0.35
    POSITIVE LOGITS
    adhi
    0.42
    틱
    0.41
     Buffer
    0.40
     경
    0.40
     buff
    0.39
    wau
    0.39
     trade
    0.39
     Portfolio
    0.38
     begrü
    0.38
     SSO
    0.38
    Activations Density 0.004%

    No Known Activations