© 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. 24358
    Prev
    Next
    INDEX
    Explanations

    early age developments

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

    development, growth, and history

    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
     Occasionally
    0.36
    ю
    0.36
     deeply
    0.35
     شبه
    0.35
     lightly
    0.35
    పే
    0.35
     mermaid
    0.35
    뱃
    0.35
    voicing
    0.34
     pě
    0.34
    POSITIVE LOGITS
     পরবর্তীতে
    0.60
     പിന്നീട്
    0.58
     senere
    0.56
     வளர்
    0.55
    æss
    0.55
     decades
    0.54
    后来
    0.52
    arriv
    0.52
     ترقی
    0.52
     दशकों
    0.52
    Activations Density 0.111%

    No Known Activations