© 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. 65010
    Prev
    Next
    INDEX
    Explanations

    learner, datab, URLs

    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
    󠁳
    -0.83
    íc
    -0.80
     genotype
    -0.75
     സ്
    -0.74
    資産
    -0.73
    NODE
    -0.71
    VEL
    -0.71
    bibitem
    -0.71
    =\""
    -0.70
     Synag
    -0.69
    POSITIVE LOGITS
    Learner
    1.09
     datab
    0.94
     learner
    0.91
    datab
    0.91
    learner
    0.90
     Learner
    0.88
    xb
    0.83
    JMP
    0.83
     xb
    0.83
    URLs
    0.80
    Activations Density 0.003%

    No Known Activations