© 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. 54593
    Prev
    Next
    INDEX
    Explanations

    running projects

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

    supply chain logistics and knowledge

    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
    患者
    0.51
     pazienti
    0.51
    ρες
    0.46
    \}_{
    0.46
    ｨ
    0.46
     пациен
    0.45
    であれば
    0.45
    ╠
    0.45
     значения
    0.45
    したのは
    0.45
    POSITIVE LOGITS
    pping
    0.51
     Lie
    0.47
    ach
    0.46
    usage
    0.46
    ின்
    0.45
    hak
    0.45
    eas
    0.42
     Pry
    0.42
    cie
    0.42
    achsen
    0.42
    Activations Density 0.000%

    No Known Activations