© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149140
    Prev
    Next
    INDEX
    Explanations

    weather today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    腐
    0.69
    (&(*
    0.64
     Helvetica
    0.63
     হাইকমি
    0.60
    мени
    0.59
     मातृ
    0.59
     কাব্য
    0.59
    Descriptors
    0.59
     मीडियम
    0.58
    aundice
    0.58
    POSITIVE LOGITS
     ATPase
    0.78
     ak
    0.74
     रैली
    0.74
     obed
    0.72
     ati
    0.72
    聲
    0.72
    蘄
    0.72
    َات
    0.70
    oclip
    0.69
    to
    0.65
    Activations Density 0.001%

    No Known Activations