© 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. 22-GEMMASCOPE-2-RES-65K
    7. 6011
    Prev
    Next
    INDEX
    Explanations

    come with or from

    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_22_width_65k_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
    1.23
    دع
    1.05
    𝘄
    1.04
    ところ
    1.00
    schap
    1.00
    sand
    0.98
     местности
    0.97
    กิน
    0.96
    នា
    0.95
    )++;
    0.95
    POSITIVE LOGITS
     létre
    1.55
    不及
    1.29
     knocking
    1.27
     fruition
    1.22
    ตรฐาน
    1.20
     undone
    1.19
    packaged
    1.13
     forth
    1.12
    uiden
    1.11
     crashing
    1.10
    Activations Density 0.034%

    No Known Activations