© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 38216
    Prev
    Next
    INDEX
    Explanations

    visual interactions, cell lymphoma, Whitney, effects, device, solve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ە
    1.89
    ت
    1.80
    не
    1.76
    ्य
    1.65
    ด
    1.59
     pytanie
    1.55
     ništa
    1.53
    ף
    1.53
     veliko
    1.52
    ные
    1.50
    POSITIVE LOGITS
    ן
    1.53
    us
    1.45
    SH
    1.36
    cible
    1.36
    est
    1.30
    ug
    1.28
     grout
    1.28
    pl
    1.27
     descent
    1.26
    )|^{
    1.26
    Activations Density 0.000%

    No Known Activations