© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3309
    Prev
    Next
    INDEX
    Explanations

    influences starting

    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_31_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
     accordingly
    0.51
    </h2>
    0.46
    ,...
    0.44
     wellknown
    0.43
    U
    0.42
    Y
    0.42
    zzi
    0.41
    Mos
    0.40
    W
    0.40
    <eos>
    0.40
    POSITIVE LOGITS
     wirklich
    0.66
    本当に
    0.63
     opravdu
    0.61
     vraiment
    0.60
     após
    0.57
    ほん
    0.57
    出来る
    0.56
     insanely
    0.56
     perchè
    0.55
     piu
    0.55
    Activations Density 0.347%

    No Known Activations