© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84378
    Prev
    Next
    INDEX
    Explanations

    initials in names

    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
     through
    -1.61
     at
    -1.61
     the
    -1.56
    Они
    -1.56
     what
    -1.53
     और
    -1.52
     And
    -1.50
    мне
    -1.48
    <td>
    -1.47
    viembre
    -1.46
    POSITIVE LOGITS
     acidente
    1.88
     começo
    1.87
     biß
    1.80
    偸
    1.72
    8
    1.70
    0
    1.69
     cuja
    1.67
     outono
    1.65
     mangiare
    1.65
     verão
    1.64
    Activations Density 0.115%

    No Known Activations