© 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-16K
    4. 977
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ك
    1.98
    و
    1.79
    z
    1.76
    k
    1.63
    ל
    1.55
    ل
    1.53
    c
    1.50
    b
    1.41
    on
    1.30
    l
    1.28
    POSITIVE LOGITS
     výrob
    1.55
     bijvoorbeeld
    1.37
     sebagaimana
    1.37
     wrenches
    1.35
    ायक
    1.34
     padrões
    1.34
     angegeben
    1.34
     окружающей
    1.34
     kategorie
    1.34
     Schrödinger
    1.31
    Activations Density 0.290%

    No Known Activations