© 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. 34895
    Prev
    Next
    INDEX
    Explanations

    JavaScript array/string methods

    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
     (
    -1.32
     can
    -1.16
    着她
    -1.16
    ).
    -1.13
    g
    -1.09
     such
    -1.08
     also
    -1.07
     gan
    -1.02
    いても
    -1.02
     avi
    -1.00
    POSITIVE LOGITS
    每個
    1.30
    嵴
    1.30
     setiap
    1.26
    Maar
    1.20
    ēju
    1.17
    たびに
    1.17
     mijne
    1.16
    足りない
    1.16
    camping
    1.15
    uminense
    1.14
    Activations Density 0.004%

    No Known Activations