© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13986
    Prev
    Next
    INDEX
    Explanations

    the following

    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
     its
    -1.24
     this
    -1.22
     nawet
    -1.13
    其
    -1.12
     December
    -1.05
    ですから
    -1.02
    テク
    -1.00
    Коммента
    -1.00
    savevideo
    -0.99
    ése
    -0.98
    POSITIVE LOGITS
     same
    1.78
     kinds
    1.27
     thing
    1.24
     exact
    1.20
     old
    1.19
     equivalent
    1.16
     gamle
    1.14
     stesso
    1.13
    大的
    1.11
    isn
    1.11
    Activations Density 0.080%

    No Known Activations