© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 157
    Prev
    Next
    INDEX
    Explanations

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     zodat
    0.20
    。
    0.19
     ("
    0.19
     خواهند
    0.19
     อย่า
    0.19
     eftersom
    0.19
    führen
    0.18
    ))
    0.17
    求
    0.17
     («
    0.17
    POSITIVE LOGITS
     there
    0.41
     you
    0.33
     it
    0.32
    bbene
    0.30
     somehow
    0.29
    there
    0.29
    तला
    0.28
    ølge
    0.27
    伱
    0.27
     unsure
    0.27
    Activations Density 0.448%

    No Known Activations