© 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. 84588
    Prev
    Next
    INDEX
    Explanations

    spending money

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

    individual ants in colonies

    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
    عر
    0.44
    로
    0.44
    여
    0.44
     Presidential
    0.44
    정이
    0.44
    Bs
    0.43
    8
    0.43
    i
    0.42
    фо
    0.42
     whistleblower
    0.41
    POSITIVE LOGITS
    𝐣
    0.52
    íž
    0.49
    isComposite
    0.48
     ಇದಕ್ಕೆ
    0.48
    Terminate
    0.48
    ită
    0.46
    ariş
    0.46
     Tâm
    0.46
     Hints
    0.46
    stering
    0.46
    Activations Density 0.000%

    No Known Activations