© 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. 2304
    Prev
    Next
    INDEX
    Explanations

    the word one

    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
    ب
    2.32
    ங்கிணை
    2.16
    надца
    1.99
    াদশ
    1.99
    क
    1.97
    씩
    1.97
    fourth
    1.84
     semblance
    1.84
     heck
    1.84
    ल
    1.82
    POSITIVE LOGITS
    Π
    1.78
     pulgadas
    1.77
     livres
    1.77
     meines
    1.66
    tedir
    1.65
    anje
    1.63
    ות
    1.63
    ské
    1.59
    ു
    1.58
    ই
    1.56
    Activations Density 0.038%

    No Known Activations