© 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-65K
    7. 54171
    Prev
    Next
    INDEX
    Explanations

    version numbers and dates

    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_65k_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
    HN
    0.38
     those
    0.37
    AA
    0.37
     AA
    0.35
     developing
    0.35
    u
    0.35
     strict
    0.34
    Sol
    0.34
     aj
    0.33
     acknowled
    0.33
    POSITIVE LOGITS
    스럽
    0.42
     rte
    0.42
     کہ
    0.40
    Innen
    0.39
    esteps
    0.39
     reversed
    0.38
    ették
    0.38
    ഹ്ലാദ
    0.38
    竰
    0.38
     مکمل
    0.38
    Activations Density 0.002%

    No Known Activations