© 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. 204118
    Prev
    Next
    INDEX
    Explanations

    traceable to national standards

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

    numbers and specific information

    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
    ંમે
    0.52
    埥
    0.49
    sampling
    0.48
    sede
    0.47
    linha
    0.47
    髪
    0.46
    sample
    0.46
    sé
    0.45
    apuris
    0.45
    褶
    0.44
    POSITIVE LOGITS
    ata
    0.59
     щ
    0.52
     നമ്പർ
    0.50
     ኦ
    0.49
    weig
    0.48
     öz
    0.47
     ე
    0.47
     βα
    0.46
     օ
    0.46
    angan
    0.46
    Activations Density 0.000%

    No Known Activations