© 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. 10321
    Prev
    Next
    INDEX
    Explanations

    is made of

    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
     voork
    2.42
    да
    2.37
    
    2.29
     beware
    2.24
    leistung
    2.24
    ch
    2.23
    BDF
    2.08
    ार्थी
    2.06
    Suppress
    2.06
    ход
    2.02
    POSITIVE LOGITS
    থেষ্ট
    2.31
     planks
    2.19
    ी
    2.19
    ό
    2.12
    始
    2.11
     threes
    2.07
    eny
    2.06
     canes
    2.03
     смеси
    2.00
     العافيه
    1.99
    Activations Density 0.085%

    No Known Activations