© 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. 35938
    Prev
    Next
    INDEX
    Explanations

    requirements and conditions

    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
     سپورت
    0.42
     NHS
    0.41
     preventive
    0.41
    کن
    0.41
     dietitian
    0.41
    \}.
    0.39
     URL
    0.39
    ತ
    0.39
    CN
    0.39
     addressing
    0.39
    POSITIVE LOGITS
    rinth
    0.47
    egaard
    0.47
     principalmente
    0.45
     தேர்த
    0.45
    ाराम
    0.45
     धोने
    0.45
    älfte
    0.44
    myItemId
    0.44
    चुरी
    0.44
     principalement
    0.43
    Activations Density 0.003%

    No Known Activations