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. 22-GEMMASCOPE-2-RES-16K
    4. 1309
    Prev
    Next
    INDEX
    Explanations

    code blocks and identifiers

    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_22_width_16k_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
    ፫
    0.90
     microorganism
    0.88
     microorganisms
    0.85
    ColorEffects
    0.84
     arable
    0.84
     microorgan
    0.83
     praia
    0.83
    ယာ
    0.82
    EndZ
    0.82
    unghi
    0.81
    POSITIVE LOGITS
     do
    0.71
     [
    0.71
    i
    0.68
     if
    0.65
    فل
    0.65
     i
    0.63
     um
    0.61
     nero
    0.61
    /
    0.60
     Tage
    0.60
    Activations Density 0.376%

    No Known Activations