© 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. 221546
    Prev
    Next
    INDEX
    Explanations

    numbers and financial terms

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

    acknowledges human possible close surface growth

    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
     كيف
    0.54
     tiap
    0.49
     gefragt
    0.45
    每
    0.45
    羊
    0.45
     лекар
    0.44
     每
    0.43
    紮
    0.43
    नीचर
    0.42
     வைத்திய
    0.42
    POSITIVE LOGITS
     or
    0.53
     markets
    0.45
    v
    0.45
    க்கொ
    0.45
     isotropic
    0.45
    package
    0.44
    jectory
    0.44
    mosaic
    0.44
    정
    0.44
    Plan
    0.44
    Activations Density 0.000%

    No Known Activations