© 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. 7731
    Prev
    Next
    INDEX
    Explanations

    links or syntax

    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
     on
    -2.17
     memperoleh
    -2.02
     menyiapkan
    -1.76
     from
    -1.74
     to
    -1.70
     after
    -1.69
     menetapkan
    -1.65
     Internasional
    -1.63
     three
    -1.59
     with
    -1.59
    POSITIVE LOGITS
     katun
    1.78
    ︲
    1.77
    蠓
    1.72
     you
    1.65
    those
    1.64
    ходил
    1.62
     ceux
    1.61
     banyo
    1.60
     kulak
    1.59
     býval
    1.59
    Activations Density 0.168%

    No Known Activations