© 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-262K
    7. 11169
    Prev
    Next
    INDEX
    Explanations

    keyboard shortcut

    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
    ת
    3.49
    й
    2.75
    이
    2.65
    因此
    2.59
     perceptible
    2.53
    ական
    2.50
    ు
    2.47
    能
    2.46
    ة
    2.45
    л
    2.43
    POSITIVE LOGITS
    venidos
    2.41
    lardan
    2.40
    siniz
    2.38
    𝚗
    2.35
    ned
    2.28
    𝚒
    2.23
    ्स
    2.23
    swith
    2.22
    indest
    2.19
    m
    2.18
    Activations Density 0.033%

    No Known Activations