© 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. 34-GEMMASCOPE-RES-131K
    7. 48369
    Prev
    Next
    INDEX
    Explanations

    -vs- separators

    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_34/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
    ----
    -1.12
     those
    -1.04
    >
    -1.03
    开始
    -0.99
    ---
    -0.95
    त
    -0.95
    髪
    -0.94
     began
    -0.91
    ا
    -0.91
    POSITIVE LOGITS
    =-=-=-=-
    1.54
    ˏ
    1.45
    =-=-
    1.43
    *-*-
    1.37
     $-$
    1.34
    webkit
    1.34
    様な
    1.22
    久し
    1.19
     -'
    1.17
    &-
    1.16
    Activations Density 0.144%

    No Known Activations