© 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. 116201
    Prev
    Next
    INDEX
    Explanations

    his own, is the, jump around, he claims, a poll, king size

    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
     –
    -1.02
    ­
    -0.95
     Universitäts
    -0.95
     …
    -0.88
     faggot
    -0.88
     silly
    -0.87
    @_
    -0.85
    ләр
    -0.85
     --
    -0.85
     Ã
    -0.84
    POSITIVE LOGITS
    edakan
    0.98
    bonding
    0.97
     embaraz
    0.96
     desastre
    0.94
     ™
    0.94
     parenting
    0.94
     jestem
    0.93
     подрост
    0.93
    ™,
    0.92
    borgen
    0.92
    Activations Density 0.012%

    No Known Activations