© 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. 34961
    Prev
    Next
    INDEX
    Explanations

    customizing text and content

    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
    <0x93>
    0.46
    <0xA6>
    0.45
    罗
    0.44
    描
    0.44
    糖
    0.43
    ای
    0.42
     ار
    0.42
    羅
    0.42
    ρα
    0.42
     hObject
    0.41
    POSITIVE LOGITS
     Tanzania
    0.49
     Zanzibar
    0.48
     corporations
    0.48
     anglers
    0.47
     freelancers
    0.47
     resellers
    0.47
    ennials
    0.47
     hikers
    0.46
     songwriters
    0.46
    lor
    0.46
    Activations Density 0.005%

    No Known Activations