© 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. 12-GEMMASCOPE-2-RES-262K
    7. 3171
    Prev
    Next
    INDEX
    Explanations

    no, nothing, keine, whatsoever

    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
    نا
    0.57
    ა
    0.54
     lecz
    0.53
     s
    0.52
    ل
    0.51
    Ale
    0.49
     Ro
    0.48
     عدم
    0.48
     IN
    0.47
    sz
    0.47
    POSITIVE LOGITS
     alcuna
    0.65
     alcun
    0.58
    🙅
    0.56
    📆
    0.55
     whatsoever
    0.55
    𝓭
    0.55
     никаких
    0.54
     simonsen
    0.54
     případě
    0.52
    𝘤
    0.52
    Activations Density 0.921%

    No Known Activations