© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8711
    Prev
    Next
    INDEX
    Explanations

    code blocks and programming constructs

    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
    a
    1.19
    ⅔
    1.11
     suffices
    1.07
     olefins
    1.05
    他に
    1.03
     πιο
    1.03
     headlights
    1.03
     septum
    1.03
    夠
    1.02
     использования
    1.01
    POSITIVE LOGITS
    𝗶
    1.32
     forth
    1.25
    ھ
    1.20
    𝘁
    1.13
    ्स
    1.10
    ی
    1.09
    𝗹
    1.08
    sj
    1.01
    𝘂
    0.98
    явления
    0.97
    Activations Density 0.078%

    No Known Activations