© 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. 19827
    Prev
    Next
    INDEX
    Explanations

    shatter easily

    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
    ╬
    0.43
     Ο
    0.43
    ьа
    0.43
     Narendra
    0.42
     Inoltre
    0.42
    Υ
    0.42
     ее
    0.42
     ollut
    0.41
    િટ
    0.41
    💢
    0.40
    POSITIVE LOGITS
     bikes
    0.44
     Chemicals
    0.44
     Marines
    0.43
     Gears
    0.43
     versions
    0.42
    冬
    0.42
     plumbers
    0.42
    APs
    0.41
     دو
    0.40
     Defense
    0.40
    Activations Density 0.005%

    No Known Activations