© 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. 10382
    Prev
    Next
    INDEX
    Explanations

    Flutter UI declarations

    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
    ="@+
    1.66
    ৌম
    1.57
    ﻞ
    1.52
    ्राफी
    1.50
     Reliability
    1.48
    gateTime
    1.47
     produziert
    1.47
     Seconds
    1.46
    ект
    1.45
     optionally
    1.43
    POSITIVE LOGITS
    р
    1.66
    र
    1.55
     bast
    1.47
     vistas
    1.41
     além
    1.41
    ר
    1.38
    ν
    1.35
    ল
    1.35
    いる
    1.35
    و
    1.34
    Activations Density 0.000%

    No Known Activations