© 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. 130600
    Prev
    Next
    INDEX
    Explanations

    option, description, comment, help

    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
     other
    -1.34
     those
    -1.26
    および
    -1.10
     pauvreté
    -1.09
     anderen
    -1.09
     altura
    -1.07
    ámos
    -1.05
     all
    -1.05
    変更
    -1.02
    bomber
    -1.02
    POSITIVE LOGITS
     "
    1.18
    {
    1.16
     aclarar
    1.15
     expresar
    1.13
     فع
    1.12
    “
    1.10
    ("
    1.10
    (
    1.09
    *
    1.08
    ="
    1.06
    Activations Density 0.001%

    No Known Activations