© 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. 186410
    Prev
    Next
    INDEX
    Explanations

    business and technical terms

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

    discounting the positive

    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
     aligned
    0.52
    aligned
    0.47
     locate
    0.47
    ৩১
    0.46
     trầm
    0.46
    渔
    0.45
     अनुसूचित
    0.45
     gravitate
    0.45
     উত্তরাধ
    0.44
    ೂರ್ವ
    0.44
    POSITIVE LOGITS
    apers
    0.48
    reich
    0.44
     perjud
    0.44
     peroxide
    0.42
     traitements
    0.41
     lekker
    0.41
     Batteries
    0.41
    ria
    0.40
    暏
    0.40
    ल्यानंतर
    0.40
    Activations Density 0.001%

    No Known Activations