© 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. 53722
    Prev
    Next
    INDEX
    Explanations

    words ending in ime or me

    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
    mär
    0.43
    េទ
    0.41
    vnd
    0.41
    ὴ
    0.41
    杪
    0.40
    𝙚
    0.40
     hsl
    0.40
    棪
    0.40
    ёв
    0.39
    ె
    0.39
    POSITIVE LOGITS
    chanical
    0.52
    chanics
    0.47
    asures
    0.45
     difficulty
    0.43
     prostitutes
    0.42
    anwhile
    0.40
     prostitute
    0.39
    kezi
    0.37
    nsan
    0.37
    ತಕ್ಕ
    0.37
    Activations Density 0.022%

    No Known Activations