© 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
    5. 16-GEMMASCOPE-2-RES-16K
    7. 552
    Prev
    Next
    INDEX
    Explanations

    academic disciplines and theories

    np_acts-logits-general · gemini-2.5-flash-lite

    logical reasoning and philosophers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    I
    0.88
    theta
    0.61
    au
    0.59
    s
    0.59
    ong
    0.57
    ных
    0.57
    triggers
    0.57
    enn
    0.57
    telling
    0.57
    de
    0.57
    POSITIVE LOGITS
    ்
    0.65
     elementi
    0.61
    ר
    0.60
    ک
    0.58
    ก
    0.58
     imati
    0.57
     analisi
    0.56
     avevo
    0.56
     edifici
    0.56
     объ
    0.56
    Activations Density 0.802%

    No Known Activations