© 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. 33101
    Prev
    Next
    INDEX
    Explanations

    radio, operated, by, rule

    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
     signer
    0.38
     closeup
    0.38
    嚀
    0.37
     вес
    0.36
     (;
    0.36
     यातायात
    0.36
     inline
    0.35
     descending
    0.35
     اینجا
    0.35
    豳
    0.35
    POSITIVE LOGITS
     dyslex
    0.42
    Fund
    0.42
     Sherlock
    0.41
    ⃞
    0.39
    Heritage
    0.39
     Deloitte
    0.39
    Jeff
    0.38
    Invest
    0.38
     Nair
    0.38
    Carrie
    0.38
    Activations Density 0.000%

    No Known Activations