© 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. 43154
    Prev
    Next
    INDEX
    Explanations

    NSW

    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
    𝗴
    1.72
    ک
    1.69
    น
    1.67
    şi
    1.66
    ்க
    1.63
    میں
    1.61
    पर्या
    1.60
    ૪
    1.59
     οποίο
    1.58
     setan
    1.56
    POSITIVE LOGITS
    ﺭ
    1.55
     וכ
    1.43
     instar
    1.38
     feat
    1.37
     feats
    1.34
     Doesn
    1.27
    لل
    1.27
    le
    1.25
     суме
    1.25
    don
    1.24
    Activations Density 0.000%

    No Known Activations