© 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
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 3698
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and structure

    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_24_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
     vết
    0.42
     leve
    0.42
     ê
    0.41
    갖
    0.41
    쾌
    0.40
     whims
    0.39
     možné
    0.38
     mối
    0.38
     lust
    0.38
    UVWXYZ
    0.37
    POSITIVE LOGITS
    ка
    0.46
    на
    0.44
    ヂストン
    0.39
    ان
    0.38
    ꜱ
    0.38
    𝙖
    0.37
    ری
    0.37
     ગ
    0.37
     acoust
    0.36
    stattung
    0.36
    Activations Density 0.003%

    No Known Activations