© 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. 55667
    Prev
    Next
    INDEX
    Explanations

    materials, colors, design, firms

    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
     had
    0.41
     المم
    0.37
     Rel
    0.37
     आइकन
    0.35
    ဟ
    0.35
     Foy
    0.35
    FM
    0.35
     Strings
    0.34
     URL
    0.34
     Controls
    0.34
    POSITIVE LOGITS
    秤
    0.44
    клар
    0.43
     verk
    0.42
    ᴦ
    0.41
    gainville
    0.41
     করিলে
    0.40
     nig
    0.40
     dout
    0.39
    ровке
    0.39
    ヴィトン
    0.38
    Activations Density 0.000%

    No Known Activations