© 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. 8789
    Prev
    Next
    INDEX
    Explanations

    revealed or AVAILABLE

    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
     coalgebras
    2.62
    ম
    2.50
     accessoires
    2.50
     enne
    2.49
     ongel
    2.45
    ات
    2.44
    воре
    2.43
    й
    2.37
     offens
    2.36
     legumes
    2.35
    POSITIVE LOGITS
    uparavant
    3.35
     través
    3.15
    서
    3.11
    spiration
    3.07
    waiting
    3.00
    varage
    2.99
     partir
    2.96
     trove
    2.93
    विश्वास
    2.84
    pathy
    2.70
    Activations Density 0.000%

    No Known Activations