© 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. 44798
    Prev
    Next
    INDEX
    Explanations

    first things first

    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
    downs
    1.44
    د
    1.40
    ্ড
    1.38
    democratic
    1.38
    {
    1.37
    disamb
    1.36
    gambar
    1.35
    д
    1.34
    gover
    1.32
    ज
    1.31
    POSITIVE LOGITS
    รส
    1.38
     možno
    1.30
     teaspoons
    1.27
    UIS
    1.21
     refracting
    1.20
    ulay
    1.20
    ARING
    1.18
     glances
    1.15
    ੁ
    1.13
    ਰ
    1.12
    Activations Density 0.000%

    No Known Activations