© 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. 31-GEMMASCOPE-2-RES-262K
    7. 182911
    Prev
    Next
    INDEX
    Explanations

    Pedro Sula, island activities, improving patient, acute coronary

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

    adhering strictly to rules

    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
    طه
    0.47
     lan
    0.46
     compter
    0.46
    Ꮰ
    0.46
    u
    0.46
    çük
    0.45
    डू
    0.45
     வரும்
    0.45
    寘
    0.45
    т
    0.45
    POSITIVE LOGITS
     сказали
    0.44
    ದಲು
    0.43
    方向に
    0.43
     (“
    0.42
     uploaded
    0.42
    的には
    0.41
     licensed
    0.41
     received
    0.40
     acquired
    0.40
     posted
    0.39
    Activations Density 0.002%

    No Known Activations