© 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-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2825
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    킬
    0.57
    NaOH
    0.57
    createServer
    0.56
    াইভ
    0.56
    ubine
    0.55
     preimage
    0.55
    淬
    0.55
     অপহরণকারী
    0.54
    醃
    0.54
     carbides
    0.52
    POSITIVE LOGITS
     financial
    4.96
    financial
    4.73
     finance
    4.59
     Financial
    4.59
    Financial
    4.56
     finances
    4.55
     финансо
    4.44
     finans
    4.43
     finan
    4.42
     FINANCIAL
    4.26
    Activations Density 1.110%

    No Known Activations