© 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. 116740
    Prev
    Next
    INDEX
    Explanations

    `named` or `Name` followed by identifier

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

    html input field names

    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
     необхідно
    0.47
    镙
    0.47
     démontré
    0.47
     சந்தேக
    0.47
     ಪೊಲೀ
    0.46
     стаўкі
    0.46
    vedere
    0.46
     науки
    0.45
    LaunchScheme
    0.45
     Еўро
    0.44
    POSITIVE LOGITS
     _
    0.59
     __
    0.53
    _
    0.50
     "_
    0.50
     members
    0.49
    id
    0.48
     cmd
    0.48
     {
    0.47
     components
    0.47
     the
    0.47
    Activations Density 0.003%

    No Known Activations