© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84715
    Prev
    Next
    INDEX
    Explanations

    up the, website/, deadlines with, exhaust ducts

    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
    د
    0.45
    conducting
    0.44
    durch
    0.41
     Elabor
    0.41
    اي
    0.40
    ক
    0.40
    conduct
    0.40
    اک
    0.39
    智慧
    0.39
    d
    0.39
    POSITIVE LOGITS
     mascara
    0.48
     marker
    0.46
     درسنا
    0.45
    ctive
    0.44
    Marker
    0.44
     destiny
    0.44
     Markers
    0.44
    悹
    0.43
     typing
    0.42
     januar
    0.42
    Activations Density 0.001%

    No Known Activations