© 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-16K
    7. 3432
    Prev
    Next
    INDEX
    Explanations

    "

    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_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
    THING
    1.62
    s
    1.45
    ्स
    1.44
     edizione
    1.30
     enk
    1.29
    ς
    1.25
    ק
    1.22
     đôi
    1.20
     epicenter
    1.19
    𝐬
    1.19
    POSITIVE LOGITS
    an
    2.58
    ان
    2.28
    на
    2.00
    quele
    1.91
    ל
    1.85
    ри
    1.82
    larda
    1.80
    কে
    1.77
    ل
    1.77
    quela
    1.76
    Activations Density 0.349%

    No Known Activations