© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93457
    Prev
    Next
    INDEX
    Explanations

    HTML tags and URIs

    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
    Ang
    -0.75
     connessione
    -0.73
    kesha
    -0.71
    Mə
    -0.70
    onians
    -0.68
    ures
    -0.68
    tral
    -0.68
    вного
    -0.67
    layın
    -0.67
     extended
    -0.67
    POSITIVE LOGITS
     chiropractic
    0.74
     decrypted
    0.72
     runaway
    0.68
    ⇔
    0.67
    Pods
    0.65
     einverstanden
    0.64
    dé
    0.64
     comida
    0.63
     missionary
    0.63
    конча
    0.62
    Activations Density 0.071%

    No Known Activations