© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1315
    Prev
    Next
    INDEX
    Explanations

    past events and history

    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_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
    в
    3.00
    on
    2.83
     powie
    2.78
     wint
    2.76
     triplets
    2.64
    তীশ
    2.54
    Ԁ
    2.44
     pihak
    2.43
    ွေ
    2.42
    hect
    2.35
    POSITIVE LOGITS
    س
    2.76
     glories
    2.72
     enmity
    2.71
    शेष
    2.71
    طة
    2.69
     austenite
    2.68
    े
    2.68
     großen
    2.66
    énés
    2.53
    尤
    2.52
    Activations Density 0.309%

    No Known Activations