© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115234
    Prev
    Next
    INDEX
    Explanations

    forced awakening

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

    medical side effects

    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_31_width_262k_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
    chave
    0.46
     الترم
    0.46
    meta
    0.45
    arele
    0.44
    引领
    0.44
    libro
    0.44
     എത്ത
    0.44
    .");
    0.43
    P
    0.43
    étrique
    0.42
    POSITIVE LOGITS
     guna
    0.55
    獣
    0.50
     McManus
    0.48
     좋은
    0.48
     dino
    0.47
     MCSF
    0.46
    াবাদ
    0.45
     тара
    0.45
    ပ
    0.45
    ების
    0.44
    Activations Density 0.004%

    No Known Activations