© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129387
    Prev
    Next
    INDEX
    Explanations

    android application and intent related code

    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
    Varför
    -1.46
    튿
    -1.43
     catég
    -1.40
     Años
    -1.39
     continuer
    -1.34
    /}.
    -1.33
    konstruktion
    -1.30
     Dimensiones
    -1.30
    MÁS
    -1.29
    蟊
    -1.29
    POSITIVE LOGITS
     has
    1.98
     in
    1.84
     what
    1.74
     made
    1.51
     all
    1.49
     from
    1.48
     with
    1.48
     any
    1.46
     and
    1.45
    </strong>
    1.40
    Activations Density 0.056%

    No Known Activations