© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16364
    Prev
    Next
    INDEX
    Explanations

    server resources used

    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_22/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
    Reps
    -0.81
     basteln
    -0.80
    Included
    -0.79
    꺼
    -0.79
     Included
    -0.78
     الحكم
    -0.78
    évaluateur
    -0.76
    цкого
    -0.75
    Viv
    -0.75
    Cevap
    -0.74
    POSITIVE LOGITS
     reserved
    1.55
     used
    1.49
     available
    1.41
     freed
    1.29
     occupied
    1.23
     dedicated
    1.23
     other
    1.20
    reserved
    1.20
     use
    1.17
    Reserved
    1.16
    Activations Density 0.080%

    No Known Activations