© 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. 9203
    Prev
    Next
    INDEX
    Explanations

    network port listening

    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
    й
    0.87
     freaking
    0.77
     courage
    0.72
    м
    0.71
    ic
    0.64
    0
    0.64
    ನ್ನು
    0.63
    साठी
    0.62
     eradicate
    0.62
    ی
    0.61
    POSITIVE LOGITS
     stati
    0.72
    Rocks
    0.66
     pois
    0.65
     buil
    0.64
     essa
    0.64
    lN
    0.63
    Lunch
    0.62
    Generalized
    0.62
    Shuffle
    0.62
    larda
    0.61
    Activations Density 0.308%

    No Known Activations