© 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. 7156
    Prev
    Next
    INDEX
    Explanations

    http/https url

    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
     framför
    -1.30
     because
    -1.30
     første
    -1.29
     pirm
    -1.28
    ⁩
    -1.27
     теперь
    -1.26
     första
    -1.23
     ganska
    -1.20
    _
    -1.20
    ansicht
    -1.19
    POSITIVE LOGITS
     also
    1.63
     conversely
    1.45
    昨晚
    1.35
    则
    1.34
    睽
    1.28
    ,\\
    1.27
    Also
    1.27
     そう
    1.25
     likewise
    1.23
     particolar
    1.21
    Activations Density 0.125%

    No Known Activations