© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9259
    Prev
    Next
    INDEX
    Explanations

    district segmentation assign sample

    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_9_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
     vuelta
    1.74
    Though
    1.46
    پ
    1.45
     zwar
    1.44
     origine
    1.43
    एफ
    1.41
     முன்
    1.36
    Ο
    1.36
    특별시
    1.35
    ja
    1.35
    POSITIVE LOGITS
    oretically
    1.98
    ię
    1.95
    ić
    1.80
    т
    1.80
    at
    1.75
    ik
    1.67
    esini
    1.66
    eV
    1.65
    ्स
    1.63
    iate
    1.63
    Activations Density 0.120%

    No Known Activations