© 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. 11224
    Prev
    Next
    INDEX
    Explanations

    be or so followed by adjective/adverb

    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
    ات
    1.15
    ς
    1.10
    ের
    1.08
    ים
    1.05
    ITY
    1.03
    ی
    1.00
    s
    0.96
    ALS
    0.96
    roidism
    0.95
    sia
    0.92
    POSITIVE LOGITS
     festiv
    1.03
    𝒇
    1.00
    oooo
    0.96
    iseum
    0.94
     obej
    0.94
     cun
    0.93
    сок
    0.91
     congregate
    0.91
    লেক
    0.90
    មើ
    0.90
    Activations Density 0.099%

    No Known Activations