© 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. 62972
    Prev
    Next
    INDEX
    Explanations

    setup code or additional setup

    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
     kontaktu
    -0.84
    tissimo
    -0.84
     reçu
    -0.81
    THERS
    -0.80
     Riproduzione
    -0.79
    standigheden
    -0.79
     fighters
    -0.78
     functie
    -0.78
    AKAN
    -0.76
    Nobody
    -0.76
    POSITIVE LOGITS
     additional
    1.16
     necessary
    1.01
     further
    0.87
     électriques
    0.85
    zl
    0.79
     initialization
    0.78
     Floyd
    0.78
    ぞれ
    0.77
    tième
    0.76
     ambitious
    0.75
    Activations Density 0.003%

    No Known Activations