© 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. 77973
    Prev
    Next
    INDEX
    Explanations

    code assertions

    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
     drá
    -0.91
    Casper
    -0.87
    Được
    -0.86
    どうぞ
    -0.84
    ᠷ
    -0.82
    dois
    -0.81
    Preguntas
    -0.81
    Rasp
    -0.81
    Kreis
    -0.80
    êtres
    -0.78
    POSITIVE LOGITS
    !
    1.34
     there
    1.20
     !
    1.16
    (!
    1.08
    !"
    1.07
     !"
    1.05
    !'
    0.97
    false
    0.96
    !,
    0.94
    !(
    0.93
    Activations Density 0.004%

    No Known Activations