© 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. 15080
    Prev
    Next
    INDEX
    Explanations

    get to

    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
     when
    -1.55
     maravillosa
    -1.52
     Hauses
    -1.51
     for
    -1.47
     Виктор
    -1.45
     він
    -1.41
     завжди
    -1.35
    *
    -1.34
     by
    -1.34
    </h2>
    -1.33
    POSITIVE LOGITS
     وفا
    1.44
    」,
    1.42
     recently
    1.42
    Отзывы
    1.41
     Luego
    1.40
     regelmäßig
    1.39
    ৢ
    1.37
    OTROS
    1.35
     esame
    1.35
    izien
    1.34
    Activations Density 0.013%

    No Known Activations