© 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. 219949
    Prev
    Next
    INDEX
    Explanations

    phrases after certain words

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

    nuclear reactions, Hybrid, Nerv

    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
     Passo
    0.49
    =""><
    0.42
     Semaphore
    0.42
     Nomor
    0.42
     passo
    0.41
    ИН
    0.40
    סה
    0.40
     number
    0.40
     Holes
    0.40
     batik
    0.40
    POSITIVE LOGITS
    嘊
    0.53
     COSTS
    0.52
    quả
    0.52
    DBMS
    0.50
    
    0.50
    ২৩
    0.48
     meteen
    0.48
    ルイ
    0.47
    送料
    0.47
    tmux
    0.47
    Activations Density 0.000%

    No Known Activations