© 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. 85846
    Prev
    Next
    INDEX
    Explanations

    web development and services

    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
    琑
    -3.23
    猡
    -3.19
    "> 
    -3.14
    豨
    -3.13
    骘
    -3.13
    ſſen
    -3.09
    ’).
    -3.08
    歘
    -2.98
    ⢅
    -2.94
    🩻
    -2.89
    POSITIVE LOGITS
    3
    3.84
    0
    3.73
    9
    3.72
    -
    3.39
     '
    3.36
    These
    3.33
    When
    3.31
    1
    3.30
    This
    3.25
    5
    3.22
    Activations Density 0.017%

    No Known Activations