© 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. 12068
    Prev
    Next
    INDEX
    Explanations

    words ending in al

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

    words ending in -ological, -ational, -ual

    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
    يل
    0.84
     sogenannte
    0.83
     sogenannten
    0.77
    り
    0.73
     பேர்
    0.73
    ഡ്
    0.71
    كي
    0.71
    quela
    0.70
    സ്
    0.70
    तील
    0.70
    POSITIVE LOGITS
    ity
    0.83
    0.70
    ITY
    0.64
    AND
    0.59
    didn
    0.59
     excesses
    0.58
     fervor
    0.57
     ۔
    0.56
    iy
    0.55
    ME
    0.55
    Activations Density 0.505%

    No Known Activations