© 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. 124449
    Prev
    Next
    INDEX
    Explanations

    individual interview

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

    incremental improvements

    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
    _
    0.55
     ስርዓ
    0.53
     시스템
    0.52
     soorten
    0.49
     က
    0.48
     monasteries
    0.47
     도시
    0.47
     설치
    0.46
     বক্স
    0.45
     empires
    0.45
    POSITIVE LOGITS
    AN
    0.59
    ฟ
    0.49
    '
    0.48
    H
    0.45
    an
    0.45
     выда
    0.44
    署
    0.44
    ία
    0.44
    講師
    0.43
    ана
    0.42
    Activations Density 0.000%

    No Known Activations