© 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. 16-GEMMASCOPE-2-RES-262K
    7. 107234
    Prev
    Next
    INDEX
    Explanations

    Hubble Constant

    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_16_width_262k_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
    ו
    0.69
    은
    0.68
     isn
    0.60
    的应用
    0.60
    و
    0.58
     ruining
    0.57
     komt
    0.57
     पौराणिक
    0.57
     profite
    0.56
     absences
    0.55
    POSITIVE LOGITS
    0
    0.70
    create
    0.66
    Toggle
    0.66
    T
    0.64
    O
    0.63
    Set
    0.63
     (
    0.62
    Create
    0.61
    Star
    0.60
    TRUE
    0.59
    Activations Density 0.000%

    No Known Activations