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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24033
    Prev
    Next
    INDEX
    Explanations

    ค followed by Thai consonant/vowel clusters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     ڈالر
    0.43
     Fragmentation
    0.38
    PAPER
    0.38
     విశ
    0.37
    항
    0.37
    ೃಷ್ಟ
    0.37
    स्टिव
    0.37
     засе
    0.35
     લાખ
    0.35
    铯
    0.35
    POSITIVE LOGITS
    บคุม
    0.41
     comien
    0.40
     bà
    0.39
     köl
    0.38
    คคล
    0.37
    ṇ
    0.37
     dioxide
    0.37
     thinks
    0.36
    一旦
    0.36
     costs
    0.36
    Activations Density 0.001%

    No Known Activations