© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99506
    Prev
    Next
    INDEX
    Explanations

    trezor.messages.TxInputType

    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
    thermia
    -0.85
    Marc
    -0.71
     climb
    -0.70
    かわらず
    -0.69
     egal
    -0.69
    骨折
    -0.69
     cât
    -0.68
     Editor
    -0.68
    scanning
    -0.68
     editor
    -0.67
    POSITIVE LOGITS
    句话
    0.82
    ituation
    0.81
     comenzado
    0.81
    𝗷
    0.76
    ộm
    0.74
     fotografie
    0.73
    %);
    0.73
     potre
    0.72
     caracteriza
    0.72
    mayer
    0.72
    Activations Density 0.001%

    No Known Activations