© 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. 61744
    Prev
    Next
    INDEX
    Explanations

    your computer

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

    words ending in -able, -ing, -ent

    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
    窕
    0.47
    atthaya
    0.46
     ढु
    0.46
     लगती
    0.46
     場所
    0.46
     話
    0.45
    Location
    0.45
     कालीन
    0.45
    location
    0.44
     determinado
    0.44
    POSITIVE LOGITS
    צ
    0.51
     IMP
    0.47
    መ
    0.46
    blit
    0.46
     YG
    0.46
     können
    0.45
    сар
    0.45
    рама
    0.43
    ²/
    0.43
     portfolios
    0.43
    Activations Density 0.000%

    No Known Activations