© 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. 85880
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     vosotros
    -0.99
     Völ
    -0.94
    Cześć
    -0.94
    ンドウ
    -0.92
    Например
    -0.91
    punten
    -0.91
    Dach
    -0.91
    Scooby
    -0.88
    便利な
    -0.88
    Liar
    -0.88
    POSITIVE LOGITS
    mak
    1.21
    y
    1.19
    logical
    1.13
    ik
    1.13
    ations
    1.12
    n
    1.02
    er
    1.02
    ing
    1.02
     дальней
    0.98
    zz
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.