© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 44459
    Prev
    Next
    INDEX
    Explanations

    VPN, server, inference

    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
    ار
    0.84
     домашних
    0.80
     furry
    0.78
    炊
    0.78
     electroweak
    0.77
     linkage
    0.76
     intracranial
    0.75
     guar
    0.74
     disobedience
    0.73
    itarian
    0.73
    POSITIVE LOGITS
    Becoming
    0.84
    begin
    0.82
    by
    0.82
    इस
    0.81
    ningar
    0.80
    poem
    0.80
    Bibli
    0.79
    as
    0.78
    ᐅ
    0.78
    use
    0.77
    Activations Density 0.000%

    No Known Activations