© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1420
    Prev
    Next
    INDEX
    Explanations

    VAR, training, showcase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Histogram
    1.03
    Pending
    0.93
    Converting
    0.92
    𝘵
    0.88
    )|^
    0.87
    $.
    0.87
    numpy
    0.85
    जानकारी
    0.84
    .")]
    0.84
     andDevice
    0.83
    POSITIVE LOGITS
     cottage
    0.99
     showcase
    0.94
     idyllic
    0.93
     battered
    0.91
     variegated
    0.88
     renaissance
    0.88
     enjoyable
    0.88
     boutique
    0.87
     indulgent
    0.86
     Cottage
    0.86
    Activations Density 0.000%

    No Known Activations