© 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. 31-GEMMASCOPE-2-RES-65K
    7. 61472
    Prev
    Next
    INDEX
    Explanations

    both or all

    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
     నిర్ణ
    0.38
     GRE
    0.37
    Lowest
    0.37
     系列
    0.36
    ᱚ
    0.36
    具体的な
    0.36
    Genre
    0.36
    XPATH
    0.36
    름
    0.35
     ።
    0.35
    POSITIVE LOGITS
     BOTH
    0.80
     both
    0.75
    both
    0.73
     only
    0.69
     únicamente
    0.69
    only
    0.69
     Both
    0.68
    Both
    0.67
     uniquement
    0.66
     ONLY
    0.65
    Activations Density 0.098%

    No Known Activations