© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158355
    Prev
    Next
    INDEX
    Explanations

    little things and quantities

    np_acts-logits-general · gemini-2.5-flash-lite

    little followed by descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    泰
    0.52
    مراجع
    0.46
    Fon
    0.46
    ጇ
    0.45
     লইয়া
    0.44
    Transformers
    0.43
    汉
    0.42
    ಲ್ಲೂ
    0.42
    Frag
    0.42
    톰
    0.42
    POSITIVE LOGITS
     z
    0.48
     globules
    0.48
     waktu
    0.47
     perpet
    0.45
     sockfd
    0.44
     وضعیت
    0.44
     kompos
    0.44
     hidrat
    0.43
     mantras
    0.43
    óso
    0.43
    Activations Density 0.003%

    No Known Activations