© 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. 65262
    Prev
    Next
    INDEX
    Explanations

    what follows "any"

    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
     السياس
    -1.40
     Nasional
    -1.29
    >=</
    -1.27
    😜
    -1.24
    чня
    -1.24
     hänen
    -1.24
     kompeti
    -1.22
    migrationBuilder
    -1.21
     Amerikaanse
    -1.20
    我们
    -1.17
    POSITIVE LOGITS
     maybe
    1.52
     mostly
    1.34
     or
    1.25
     their
    1.23
     Vielleicht
    1.21
     see
    1.20
     may
    1.19
    窺
    1.18
     partly
    1.18
     like
    1.17
    Activations Density 0.252%

    No Known Activations