© 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. 102728
    Prev
    Next
    INDEX
    Explanations

    words starting with 'un' or 'pre'

    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
     
    -3.53
     improve
    -2.86
    ?
    -2.78
     locate
    -2.64
    ↵↵
    -2.59
     troublesome
    -2.50
     Erweiterung
    -2.39
     regain
    -2.38
     navigate
    -2.36
     stumbling
    -2.33
    POSITIVE LOGITS
     стоковые
    3.22
    AdvEx
    2.94
    оргаш
    2.94
     itſelf
    2.84
    s
    2.83
    メリカ
    2.77
    r
    2.77
    ڧ
    2.70
     egens
    2.67
     himſelf
    2.66
    Activations Density 0.010%

    No Known Activations