© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50643
    Prev
    Next
    INDEX
    Explanations

    expression parser visitor

    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
     deals
    0.39
     JSX
    0.38
     Deals
    0.38
     Containers
    0.37
    წვ
    0.37
    탭
    0.37
     লিখেছেন
    0.36
     Sil
    0.36
     태
    0.36
     रहेंगे
    0.35
    POSITIVE LOGITS
    pass
    0.42
    trans
    0.42
    ENTIAL
    0.42
    burn
    0.42
    phosph
    0.41
    fer
    0.39
    although
    0.39
    du
    0.39
    acid
    0.38
    changes
    0.38
    Activations Density 0.021%

    No Known Activations