Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 1856
    Prev
    Next
    INDEX
    Explanations

    praeruptora

    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_17_width_65k_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
    զ
    1.00
    quez
    0.92
     unob
    0.92
     pengh
    0.82
     mẽ
    0.79
     musically
    0.79
     quadro
    0.79
    𝗻
    0.79
    तोड़
    0.78
     adul
    0.77
    POSITIVE LOGITS
    al
    1.30
    م
    1.30
    ು
    1.23
    ap
    1.19
    v
    1.19
    d
    1.14
    র
    1.14
    nown
    1.13
    at
    1.12
    ponsored
    1.12
    Activations Density 0.360%

    No Known Activations