© 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. 69825
    Prev
    Next
    INDEX
    Explanations

    numerical specifications

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

    line-height 1.6

    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
    ప్రత్యర్థి
    0.48
    戕
    0.46
    izantes
    0.46
    侵害
    0.46
     दरवाजे
    0.45
     महज
    0.45
     वेडिंग
    0.45
     Казіно
    0.44
     हिमाचल
    0.44
    セプト
    0.44
    POSITIVE LOGITS
     /*
    0.55
     slower
    0.47
    ↵
    0.46
    ↵↵
    0.45
     \
    0.45
     czę
    0.45
     slow
    0.45
     Slow
    0.45
    Slow
    0.45
     strut
    0.43
    Activations Density 0.000%

    No Known Activations