© 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. 73189
    Prev
    Next
    INDEX
    Explanations

    FFmpeg, MPEG, Nitro

    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
    ︲
    -1.62
    蠖
    -1.50
    "
    -1.46
    acterísticas
    -1.41
    如同
    -1.40
    臯
    -1.36
    是很
    -1.34
    The
    -1.34
     taką
    -1.28
     каждо
    -1.27
    POSITIVE LOGITS
    </strong>
    2.03
    ilita
    1.35
    鉻
    1.31
    isesti
    1.27
     sobrevivir
    1.27
    t
    1.26
     Option
    1.24
    òn
    1.21
     dobré
    1.20
     Frage
    1.20
    Activations Density 0.008%

    No Known Activations