© 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. 31-GEMMASCOPE-2-RES-262K
    7. 202136
    Prev
    Next
    INDEX
    Explanations

    API, GPU, Gaming, Topology, Detection

    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
    он
    0.53
    сла
    0.52
    ωσ
    0.51
    ويب
    0.51
    وبر
    0.50
    дою
    0.50
    μά
    0.50
    녠
    0.49
    يش
    0.49
    вица
    0.49
    POSITIVE LOGITS
     strongly
    0.52
    Side
    0.48
     obtained
    0.46
     eradicated
    0.46
    Split
    0.44
    in
    0.44
     troops
    0.43
     truly
    0.42
            
    0.42
     Separate
    0.42
    Activations Density 0.000%

    No Known Activations