© 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. 11897
    Prev
    Next
    INDEX
    Explanations

    driven by, giving you

    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
     الجهاز
    1.20
     Nesse
    1.15
     Personally
    1.13
    ‫
    1.13
     Ната
    1.12
     Mentre
    1.12
     पंतप्रधान
    1.10
     було
    1.10
    geqslant
    1.10
    ieger
    1.07
    POSITIVE LOGITS
    та
    1.28
    an
    1.25
    teen
    1.21
     করছি
    1.15
     disciple
    1.14
    s
    1.10
    clickable
    1.10
     attn
    1.10
    нное
    1.08
    Vic
    1.07
    Activations Density 0.000%

    No Known Activations