© 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. 64496
    Prev
    Next
    INDEX
    Explanations

    message key

    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
     bose
    -0.82
     alin
    -0.75
     laf
    -0.73
    ölkerung
    -0.68
     WRAP
    -0.68
     Schae
    -0.67
    cektir
    -0.66
     attachment
    -0.65
     miy
    -0.64
     SERVICES
    -0.64
    POSITIVE LOGITS
     wysokiej
    0.69
     Confederate
    0.68
     照明
    0.67
     fér
    0.66
    三郎
    0.65
     skilled
    0.65
     drewna
    0.64
    Molly
    0.63
    pH
    0.63
     gunshot
    0.63
    Activations Density 0.051%

    No Known Activations