© 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. 16-GEMMASCOPE-2-RES-262K
    7. 33644
    Prev
    Next
    INDEX
    Explanations

    IP addresses and codes

    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_16_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
    IZING
    0.62
    <unused173>
    0.58
     Guant
    0.58
     BOTH
    0.57
     определён
    0.57
    Pharmacy
    0.57
     हाईकोर्ट
    0.56
    <unused8>
    0.55
     Docket
    0.55
    ANZ
    0.55
    POSITIVE LOGITS
     man
    0.61
    а
    0.58
     n
    0.57
     user
    0.57
     col
    0.57
     code
    0.56
     which
    0.55
     car
    0.55
     version
    0.55
     m
    0.53
    Activations Density 0.034%

    No Known Activations