© 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. 77219
    Prev
    Next
    INDEX
    Explanations

    gone, lost, or wild

    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
    ENT
    -1.01
    鷓
    -0.98
    dice
    -0.98
     вспом
    -0.95
    Läh
    -0.93
     passport
    -0.93
     confe
    -0.92
     iko
    -0.91
     allarg
    -0.90
    POSITIVE LOGITS
     astray
    1.15
     Gone
    1.13
    Gone
    1.12
     from
    1.11
    rogue
    0.98
     feasting
    0.97
     overboard
    0.94
     GONE
    0.93
    phenols
    0.91
     gone
    0.89
    Activations Density 0.006%

    No Known Activations