© 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. 31-GEMMASCOPE-2-RES-65K
    7. 50588
    Prev
    Next
    INDEX
    Explanations

    credentials, permissions, structure, options

    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_31_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
     metaphysical
    0.52
    configured
    0.51
     Doherty
    0.49
     computing
    0.48
    늄
    0.48
    nsic
    0.48
    ards
    0.48
     iconic
    0.47
     півні
    0.46
     skirt
    0.45
    POSITIVE LOGITS
     Authorization
    0.48
    /
    0.45
    字母
    0.44
    मला
    0.44
    噸
    0.43
    gunaan
    0.43
    FAO
    0.43
    ANTH
    0.42
     memakai
    0.42
     Manual
    0.40
    Activations Density 0.002%

    No Known Activations