© 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. 48476
    Prev
    Next
    INDEX
    Explanations

    early year

    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
    早
    0.63
    early
    0.61
     early
    0.54
     早
    0.53
     Early
    0.53
    Early
    0.52
     EARLY
    0.48
    late
    0.47
     late
    0.47
     früh
    0.46
    POSITIVE LOGITS
    ❐
    0.38
    pV
    0.37
    bilt
    0.37
     Lorsqu
    0.37
    пустить
    0.37
    ence
    0.37
    orsese
    0.37
    нул
    0.36
    pel
    0.36
     Tochter
    0.36
    Activations Density 0.015%

    No Known Activations