© 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. 172
    Prev
    Next
    INDEX
    Explanations

    billions of parameters

    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
     använd
    1.32
     Enix
    1.30
     Cliquez
    1.30
    ल
    1.29
    ﹐
    1.27
     erbjuder
    1.25
     highlands
    1.23
     Schrö
    1.21
     Cál
    1.21
    ний
    1.19
    POSITIVE LOGITS
    ए
    1.41
    i
    1.38
    dler
    1.27
    d
    1.26
    тся
    1.24
    AR
    1.22
    kte
    1.16
    এম
    1.16
    dı
    1.15
    不然
    1.13
    Activations Density 0.038%

    No Known Activations