© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15612
    Prev
    Next
    INDEX
    Explanations

    package and plugins

    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
    ........
    -1.16
     been
    -1.15
     nég
    -1.08
    TIMORE
    -1.08
    .......
    -1.04
    When
    -1.03
    iteln
    -1.03
    ......
    -1.03
     Initially
    -0.99
     If
    -0.99
    POSITIVE LOGITS
     genoux
    1.20
    ggy
    1.09
    nemers
    1.05
    richtet
    1.05
     procedimientos
    1.04
    ichert
    1.03
     thẻ
    1.02
    ḿ
    1.02
    räume
    1.02
     technisch
    1.01
    Activations Density 0.000%

    No Known Activations