© 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. 14457
    Prev
    Next
    INDEX
    Explanations

    foreign tokens and 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
     jelent
    -1.49
     Dados
    -1.40
    motorola
    -1.39
    neko
    -1.35
    jess
    -1.30
     downloaden
    -1.28
    ையில்
    -1.27
     cultiv
    -1.27
     ''
    -1.25
    philips
    -1.24
    POSITIVE LOGITS
    9
    1.43
     trochę
    1.41
     they
    1.37
     you
    1.33
    緞
    1.32
     utilizzato
    1.30
     alimentaria
    1.30
     but
    1.30
    giarism
    1.29
    3
    1.28
    Activations Density 0.111%

    No Known Activations