© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 119807
    Prev
    Next
    INDEX
    Explanations

    diverse languages and specific items

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

    Bash Support

    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
    Negative Logits
     demeanor
    0.51
    Confidence
    0.44
    Calibration
    0.42
    PM
    0.41
    ZM
    0.41
    DNA
    0.41
     向
    0.41
    就
    0.40
    中使用
    0.40
     PTC
    0.40
    POSITIVE LOGITS
    ógrafo
    0.52
    ون
    0.51
    য়
    0.49
    ského
    0.45
     nacido
    0.45
    ícím
    0.45
    લ્લા
    0.44
    street
    0.44
     längre
    0.44
     nặng
    0.44
    Activations Density 0.000%

    No Known Activations