© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83911
    Prev
    Next
    INDEX
    Explanations

    back off

    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
    cookie
    -0.84
    зани
    -0.74
    gettimeofday
    -0.74
    LOCK
    -0.71
    ómicos
    -0.69
    》.
    -0.69
     BMC
    -0.68
     liber
    -0.68
     Moor
    -0.67
     consulter
    -0.67
    POSITIVE LOGITS
     backing
    4.34
     backed
    4.22
    backed
    3.52
    Backing
    3.52
     Backing
    3.44
    backing
    3.39
     backs
    2.84
     backers
    2.30
     backup
    2.28
     backups
    2.02
    Activations Density 0.045%

    No Known Activations