© 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. 1277
    Prev
    Next
    INDEX
    Explanations

    options lists

    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
    0
    1.77
    1
    1.48
    2
    1.45
    5
    1.44
    3
    1.40
    6
    1.30
    4
    1.29
    8
    1.25
    7
    1.18
    9
    1.17
    POSITIVE LOGITS
    ़
    0.97
     ও
    0.90
    和
    0.89
     and
    0.89
    SAFER
    0.87
     or
    0.86
     σχετικά
    0.85
    മാക
    0.85
    ့်
    0.84
    恝
    0.82
    Activations Density 1.342%

    No Known Activations