© 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. 76694
    Prev
    Next
    INDEX
    Explanations

    Santa + place name

    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
     کہ
    -0.90
    Oferta
    -0.77
    Esa
    -0.77
    Proceed
    -0.76
     chimiques
    -0.76
    currPos
    -0.75
     Prompt
    -0.73
     sonunda
    -0.73
     Proceed
    -0.73
    Nein
    -0.73
    POSITIVE LOGITS
     Claus
    1.63
    Santa
    1.27
     claus
    1.27
     Cruz
    1.21
     clause
    1.20
     Clause
    1.13
     Santa
    1.13
    Clause
    1.13
     Barbara
    1.11
     cruz
    1.09
    Activations Density 0.014%

    No Known Activations