© 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. 23702
    Prev
    Next
    INDEX
    Explanations

    poly

    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
    kurat
    0.41
    a
    0.41
     procurando
    0.40
     Findings
    0.38
    ள்
    0.38
     Bunda
    0.37
    agawa
    0.37
    "}
    0.37
     Road
    0.37
    !")
    0.37
    POSITIVE LOGITS
    Pol
    0.94
     Pol
    0.85
     поли
    0.77
     पोली
    0.75
     poly
    0.73
     polis
    0.71
    Poly
    0.70
     Poly
    0.68
     pol
    0.66
     POL
    0.66
    Activations Density 0.018%

    No Known Activations