© 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. 34-GEMMASCOPE-RES-131K
    7. 78702
    Prev
    Next
    INDEX
    Explanations

    article section titles

    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_34/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
    Ita
    -0.81
     macroscopic
    -0.77
     Kav
    -0.72
     Ita
    -0.71
    ētu
    -0.71
     coron
    -0.69
     entendi
    -0.68
     Pani
    -0.68
     Uri
    -0.67
    utri
    -0.66
    POSITIVE LOGITS
     Spielberg
    1.22
     Tint
    1.00
     kulak
    0.86
    CharacterOffset
    0.84
     Halliday
    0.82
    Virtual
    0.80
     Ready
    0.80
    Ready
    0.80
     Friendly
    0.78
    Spiel
    0.78
    Activations Density 0.037%

    No Known Activations