© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10543
    Prev
    Next
    INDEX
    Explanations

    lists and sequences

    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
    frak
    1.22
    fully
    1.21
    у
    1.18
     haga
    1.17
     Jangan
    1.16
     Ken
    1.14
    榀
    1.11
     Verhältnis
    1.11
    สาน
    1.11
     Lent
    1.05
    POSITIVE LOGITS
    Leod
    1.46
     discorso
    1.24
     gxf
    1.23
    $_
    1.22
     dormitorios
    1.17
    Category
    1.16
     identidade
    1.16
     atrás
    1.15
    Studies
    1.15
    turtle
    1.15
    Activations Density 0.000%

    No Known Activations