© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87444
    Prev
    Next
    INDEX
    Explanations

    also well

    np_acts-logits-general · gemini-2.5-flash-lite

    negation or contrast followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tournament
    0.47
    '
    0.47
    的时间
    0.45
    ASGI
    0.44
    ⏰
    0.44
    evening
    0.44
    কালের
    0.43
    ‘
    0.43
    halle
    0.42
    langan
    0.42
    POSITIVE LOGITS
     tableView
    0.54
     País
    0.51
     bigger
    0.49
     scoff
    0.48
     moderately
    0.48
     réaliser
    0.47
    眼里
    0.47
     geologic
    0.46
    ému
    0.46
     bothers
    0.45
    Activations Density 0.004%

    No Known Activations