© 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. 22-GEMMASCOPE-RES-131K
    7. 67488
    Prev
    Next
    INDEX
    Explanations

    characterizing descriptions

    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
     even
    -1.20
    preneurs
    -1.17
    thodoxy
    -1.12
    antism
    -1.11
     flore
    -1.09
    ——”
    -1.09
    preneurship
    -1.09
    (/^
    -1.08
    preneur
    -1.07
    caping
    -1.06
    POSITIVE LOGITS
    涉及
    1.18
     topic
    1.17
     complex
    1.15
     Requires
    1.09
     fraught
    1.06
     queste
    1.04
     betrifft
    1.02
     legte
    1.01
     sujeto
    1.00
     rất
    0.98
    Activations Density 0.112%

    No Known Activations