© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 51845
    Prev
    Next
    INDEX
    Explanations

    interactive game/app previews

    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
    Otro
    0.43
    jazz
    0.41
    Whilst
    0.38
     애니
    0.38
    loft
    0.38
     ritrov
    0.38
    演示
    0.37
    巡
    0.37
    孽
    0.37
     इन्वेस्ट
    0.37
    POSITIVE LOGITS
     retr
    0.45
     resolutions
    0.39
     resolution
    0.39
     resolução
    0.38
     Resolutions
    0.38
     late
    0.37
    ве
    0.36
     ahead
    0.36
     authority
    0.35
     rosette
    0.35
    Activations Density 0.005%

    No Known Activations