© 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. 31337
    Prev
    Next
    INDEX
    Explanations

    according to, take me, call box

    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
     ótimo
    -0.81
    펙
    -0.75
     قم
    -0.75
     Organis
    -0.74
     incre
    -0.73
     residences
    -0.72
    tsv
    -0.71
     readout
    -0.70
    )$\\
    -0.69
     touches
    -0.69
    POSITIVE LOGITS
     oport
    0.83
     plancher
    0.79
    connectivity
    0.79
    closedir
    0.79
     VAT
    0.78
     quoting
    0.78
     coleg
    0.78
     चाहते
    0.77
     sobr
    0.76
    frei
    0.76
    Activations Density 0.006%

    No Known Activations