© 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. 30907
    Prev
    Next
    INDEX
    Explanations

    Trait and state

    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
     !”
    -0.79
    ބ
    -0.78
    よく
    -0.76
     коронави
    -0.71
     hcm
    -0.71
     Schnell
    -0.70
    Atentamente
    -0.69
    зда
    -0.69
    parently
    -0.68
    кому
    -0.67
    POSITIVE LOGITS
    真ん
    0.88
     zuges
    0.77
    png
    0.77
    noks
    0.77
     Manage
    0.76
     港
    0.75
    gauss
    0.75
    깽
    0.74
    ât
    0.74
     男女
    0.74
    Activations Density 0.000%

    No Known Activations