© 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. 7566
    Prev
    Next
    INDEX
    Explanations

    numerical strings and Korean names

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

    minimal ROI, cost base

    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
    0.62
    Nicolas
    0.57
    Util
    0.55
    Scripts
    0.54
    Paris
    0.52
    Audio
    0.52
    Jessica
    0.52
    @
    0.50
    thew
    0.50
    Nicole
    0.49
    POSITIVE LOGITS
     δύο
    0.57
     vanligt
    0.55
     două
    0.54
     criterio
    0.52
     però
    0.51
     cominci
    0.51
     activación
    0.50
     verhindern
    0.50
     átomos
    0.50
     critérios
    0.50
    Activations Density 0.000%

    No Known Activations