© 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. 127403
    Prev
    Next
    INDEX
    Explanations

    sustain themselves

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

    focuses on a subject

    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
    ли
    0.51
     Jr
    0.49
    I
    0.49
    нун
    0.46
    III
    0.45
    INA
    0.44
    Jr
    0.44
     Sharpe
    0.44
    老的
    0.44
    ij
    0.44
    POSITIVE LOGITS
     sujet
    0.50
     axis
    0.47
     nozzles
    0.44
    getSource
    0.43
    ক্ষে
    0.42
     residentes
    0.42
    轴
    0.42
     embryos
    0.42
    inputSelect
    0.42
    >|</
    0.42
    Activations Density 0.001%

    No Known Activations