© 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. 152176
    Prev
    Next
    INDEX
    Explanations

    words ending in -ality

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

    amounts of a substance

    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
     compétence
    0.55
     manglid
    0.52
    amyl
    0.50
    GTBase
    0.50
    cevam
    0.49
    obutyl
    0.49
    ума
    0.48
    𒁾
    0.48
     buddhav
    0.47
     fructose
    0.47
    POSITIVE LOGITS
    z
    0.73
    hal
    0.51
    by
    0.50
    Ö
    0.50
    Son
    0.49
    Y
    0.49
    An
    0.49
     i
    0.48
    Ü
    0.48
    ż
    0.48
    Activations Density 0.000%

    No Known Activations