© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103521
    Prev
    Next
    INDEX
    Explanations

    questions or topics

    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
     Boxer
    -0.79
    žně
    -0.75
    privateKey
    -0.73
    ppets
    -0.72
     wrapper
    -0.72
    icha
    -0.71
    ッパ
    -0.71
     Winder
    -0.71
    quetas
    -0.70
    ientôt
    -0.70
    POSITIVE LOGITS
     Act
    0.83
    Act
    0.83
     act
    0.82
    Dialog
    0.73
    dare
    0.70
    Tre
    0.70
     mercenary
    0.70
    可选
    0.70
     merc
    0.69
    camiento
    0.68
    Activations Density 0.015%

    No Known Activations