© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8358
    Prev
    Next
    INDEX
    Explanations

    code delimiters and surrounding words

    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_65k_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
     sidewalks
    0.79
     aisles
    0.75
     pallets
    0.74
    Â
    0.73
    <0xC2>
    0.73
    ventions
    0.73
     adhesions
    0.72
     villages
    0.72
     webinars
    0.72
    ables
    0.71
    POSITIVE LOGITS
     」,
    0.96
     („
    0.95
     («
    0.89
    ：「
    0.89
     அவர்களுடைய
    0.89
     」
    0.88
     「
    0.87
     Acerca
    0.86
    「
    0.85
     લગભગ
    0.85
    Activations Density 0.001%

    No Known Activations