© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14173
    Prev
    Next
    INDEX
    Explanations

    programming concepts and specific dates

    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
    I
    -1.25
     of
    -1.25
    ,.
    -1.18
     I
    -1.13
     then
    -1.12
    .,
    -1.11
    의
    -1.10
    F
    -1.09
     A
    -1.07
    for
    -1.06
    POSITIVE LOGITS
    Suka
    1.23
    Seni
    1.22
    Cinta
    1.21
    Taman
    1.20
    Opel
    1.19
    Jeudi
    1.18
    Sana
    1.17
    极为
    1.13
     DISEASES
    1.13
     ferie
    1.10
    Activations Density 0.000%

    No Known Activations