© 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. 44253
    Prev
    Next
    INDEX
    Explanations

    commands, tags, and specific identifiers

    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
     speziellen
    -2.59
    x
    -2.36
     dritten
    -2.27
     noteworthy
    -2.22
     unwavering
    -2.20
     innumerable
    -2.13
     relentlessly
    -2.13
     intensely
    -2.08
     zweiten
    -2.05
     extraordinarily
    -2.05
    POSITIVE LOGITS
    {
    3.22
    ?!?
    2.89
    ,
    2.64
    1
    2.28
    ଼
    2.23
    ва
    2.17
    を知る
    2.14
     traditionelle
    2.13
    ciutto
    2.11
    ?!?!
    2.09
    Activations Density 0.035%

    No Known Activations