© 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. 15452
    Prev
    Next
    INDEX
    Explanations

    qualities and abilities

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

    conjunction of qualities

    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
    a
    0.57
    ａ
    0.51
    а
    0.45
     sebuah
    0.45
    một
    0.44
    ших
    0.44
    了一
    0.43
    一个
    0.43
    Meals
    0.42
    Ｃ
    0.42
    POSITIVE LOGITS
     inability
    0.86
     ability
    0.86
     resemblance
    0.69
     lack
    0.68
     способность
    0.66
     penchant
    0.65
     eagerness
    0.62
     tendency
    0.61
     способности
    0.61
     unwillingness
    0.61
    Activations Density 0.039%

    No Known Activations