© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 89503
    Prev
    Next
    INDEX
    Explanations

    childhood people kid

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

    conversational or dialogue fine-tuning

    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
     अंजीर
    0.52
     ρ
    0.49
    y
    0.47
    𝘆
    0.47
    𝑦
    0.46
    𝗰
    0.45
    lin
    0.45
    𝗖
    0.44
     прода
    0.44
    vitamin
    0.44
    POSITIVE LOGITS
    دف
    0.47
    ganos
    0.45
    Boards
    0.44
    Pipeline
    0.44
    Isaac
    0.44
     sekund
    0.44
    Play
    0.43
    ArrayList
    0.43
    وها
    0.42
    五年
    0.42
    Activations Density 0.001%

    No Known Activations