© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72724
    Prev
    Next
    INDEX
    Explanations

    3D depth parallax stereo vision

    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
     teacher
    -1.25
    ↵↵↵↵↵↵↵
    -1.20
     player
    -1.16
    Bool
    -1.13
    ↵↵↵
    -1.13
    跸
    -1.12
     capelli
    -1.11
    mathrm
    -1.11
    這個
    -1.11
    ↵↵↵↵↵↵↵↵↵
    -1.10
    POSITIVE LOGITS
     of
    1.42
     zaji
    1.25
     glimpses
    1.21
    其余
    1.18
     WaitForSeconds
    1.18
    它们的
    1.14
     folgender
    1.12
     Sanctions
    1.11
     manifiesta
    1.09
     its
    1.09
    Activations Density 0.100%

    No Known Activations