© 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. 58005
    Prev
    Next
    INDEX
    Explanations

    start, Christ, sunlight, analog, NH, obfuscation

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

    Rust programming language

    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
    şe
    0.51
     jau
    0.46
     javax
    0.45
     이에
    0.44
     rufis
    0.43
    şi
    0.41
    ẹn
    0.41
    u
    0.40
    agangan
    0.40
     ölüm
    0.40
    POSITIVE LOGITS
    開始
    0.50
    因子
    0.49
    皚
    0.48
     स्टार्टिंग
    0.47
    InChildren
    0.46
    楽しい
    0.46
    횃
    0.46
    ني
    0.45
    がん
    0.45
    羅
    0.45
    Activations Density 0.000%

    No Known Activations