© 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. 1346
    Prev
    Next
    INDEX
    Explanations

    many or several

    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
    $('#
    1.40
    瓏
    1.38
    MENTS
    1.33
    ्स
    1.28
    𝐬
    1.26
    hips
    1.26
    ਆ
    1.24
    lings
    1.21
    currencies
    1.21
    猬
    1.18
    POSITIVE LOGITS
    ه
    1.67
    ু
    1.65
    u
    1.51
    an
    1.50
    ção
    1.49
    त
    1.40
     dioxide
    1.32
    կ
    1.30
    у
    1.26
    й
    1.24
    Activations Density 0.166%

    No Known Activations