© 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. 10795
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    𝘋
    1.23
    િયા
    1.22
     grains
    1.21
     NPCs
    1.19
    𝐒
    1.16
    𝘢
    1.15
     responders
    1.15
     warriors
    1.15
     κάθε
    1.11
     Pued
    1.10
    POSITIVE LOGITS
    l
    1.33
    ה
    1.26
    throttle
    1.18
    hauled
    1.16
    fortunately
    1.16
    tru
    1.15
    lace
    1.15
    詳しくは
    1.15
    riture
    1.14
    y
    1.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.