© 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. 118449
    Prev
    Next
    INDEX
    Explanations

    exclusive content or licenses

    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
     Unterkunft
    -0.73
    自立
    -0.73
    liberty
    -0.66
     okuyayım
    -0.66
    subaru
    -0.66
    ={`${
    -0.64
     tío
    -0.64
     Ebert
    -0.63
     Frederick
    -0.63
    าก
    -0.63
    POSITIVE LOGITS
     exclusive
    7.47
    exclusive
    6.53
    Exclusive
    6.19
     Exclusive
    6.06
     exclusivity
    5.41
     EXCLUSIVE
    5.38
    EXCLUSIVE
    5.06
     exclusively
    5.03
    exclu
    5.03
     exclusiva
    5.00
    Activations Density 0.268%

    No Known Activations