© 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. 43110
    Prev
    Next
    INDEX
    Explanations

    veloster, vellore, velopark, velum, velocities, yvelines, velázquez

    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
    '
    -4.31
    所谓的
    -2.64
    ↵↵
    -2.56
    ᠴ
    -2.56
    ㌘
    -2.53
    }
    -2.53
     イラストレーション
    -2.53
     andre
    -2.45
     noft
    -2.36
    ."));
    -2.36
    POSITIVE LOGITS
     With
    3.42
    When
    3.03
     When
    2.97
    These
    2.92
     There
    2.88
    轶
    2.61
     These
    2.59
    If
    2.58
     Why
    2.56
    Our
    2.53
    Activations Density 0.005%

    No Known Activations