© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144654
    Prev
    Next
    INDEX
    Explanations

    following connective words

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

    collectibles, payment, software

    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
    spoon
    0.49
    ちなみに
    0.49
    lis
    0.48
    ளும்
    0.46
    땔
    0.46
    <0x89>
    0.46
    Osm
    0.46
    disc
    0.43
    <0x8A>
    0.43
    μός
    0.43
    POSITIVE LOGITS
     enthalten
    0.55
     wechsel
    0.54
     aguas
    0.49
     அரச
    0.48
     foment
    0.48
     हेम
    0.47
     weiter
    0.47
     hemorrh
    0.46
     diapers
    0.46
     portent
    0.45
    Activations Density 0.001%

    No Known Activations