© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-16K
    4. 539
    Prev
    Next
    INDEX
    Explanations

    names and entities

    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_29_width_16k_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
     outweighs
    0.86
     -
    0.85
     specify
    0.78
     (~
    0.77
     *(
    0.77
     (
    0.77
     -&
    0.75
     –
    0.75
     exists
    0.73
     typically
    0.73
    POSITIVE LOGITS
    Magic
    0.94
    Texas
    0.92
    Russian
    0.90
    Linea
    0.87
    Marine
    0.86
    Microsoft
    0.86
    Trim
    0.85
    Muscle
    0.85
    Mega
    0.85
    <unused414>
    0.85
    Activations Density 0.571%

    No Known Activations