© 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. 10-GEMMASCOPE-RES-131K
    7. 68122
    Prev
    Next
    INDEX
    Explanations

    actions and outcomes

    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_10/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
    लाइन
    -1.41
    膺
    -1.38
    ).
    -1.31
    ."
    -1.27
     auster
    -1.19
     to
    -1.16
    ↵↵
    -1.16
     ‘
    -1.15
     originally
    -1.14
     was
    -1.13
    POSITIVE LOGITS
     of
    1.92
     poprzez
    1.46
     or
    1.44
    ꈊ
    1.41
    gencias
    1.40
     gemak
    1.39
     przyczyn
    1.39
     our
    1.38
    شارة
    1.38
     Pemerintah
    1.38
    Activations Density 0.027%

    No Known Activations