© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 110901
    Prev
    Next
    INDEX
    Explanations

    MDM Systems, WalkSpeed

    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
     conhece
    0.43
    ☸
    0.39
     대한민국
    0.38
     aplicado
    0.38
     peta
    0.38
     Aap
    0.38
     imao
    0.37
    republik
    0.37
    electrolyte
    0.37
     měl
    0.37
    POSITIVE LOGITS
    ună
    0.45
    xima
    0.41
    й
    0.40
     ран
    0.38
     streng
    0.37
    rint
    0.36
     Duff
    0.35
    Duke
    0.35
    หนึ่ง
    0.35
    φυ
    0.34
    Activations Density 0.000%

    No Known Activations