© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79718
    Prev
    Next
    INDEX
    Explanations

    qualities followed by associations

    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
     and
    -1.32
     tästä
    -1.20
    但是
    -1.06
     lakh
    -1.06
    șa
    -1.03
     hänen
    -1.02
     tämän
    -1.01
     elämä
    -0.99
     olyan
    -0.98
    förm
    -0.97
    POSITIVE LOGITS
     to
    1.24
     when
    1.18
     would
    1.14
     was
    1.14
     Поэтому
    1.11
     used
    1.11
    источник
    1.09
     toward
    1.07
     importantly
    1.07
     网站
    1.05
    Activations Density 0.057%

    No Known Activations