© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20058
    Prev
    Next
    INDEX
    Explanations

    granted permission

    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
    iesti
    -1.41
     PROCEDURES
    -1.39
    蟜
    -1.38
    zember
    -1.38
     современного
    -1.28
    媪
    -1.27
    预算
    -1.26
    澳洲
    -1.26
     blick
    -1.25
    之後
    -1.23
    POSITIVE LOGITS
     összefoglal
    1.45
     sekä
    1.37
     for
    1.34
    НИМА
    1.34
    4
    1.30
     nawet
    1.30
    自律
    1.30
     sebagaimana
    1.29
    ेशा
    1.27
    鎚
    1.27
    Activations Density 0.043%

    No Known Activations