© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8364
    Prev
    Next
    INDEX
    Explanations

    the word nothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    E
    -2.14
     membri
    -2.09
     obtenir
    -2.06
    龶
    -2.03
     câbles
    -2.02
     artig
    -2.02
    閉じる
    -2.02
    Ⲉ
    -1.99
     negozio
    -1.98
     trajets
    -1.98
    POSITIVE LOGITS
     Occasionally
    2.22
     начинают
    2.20
     Therefore
    2.19
     Nonetheless
    2.14
     Until
    2.09
     the
    2.06
     Much
    2.03
     Somewhat
    2.03
     You
    2.02
    许久
    2.02
    Activations Density 0.010%

    No Known Activations