© 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. 39806
    Prev
    Next
    INDEX
    Explanations

    health and symptoms

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

    pros and cons

    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
     hereby
    0.49
    studio
    0.48
    hive
    0.46
    -
    0.45
     S
    0.44
     hear
    0.43
     diving
    0.42
     apologize
    0.42
     Excellency
    0.41
     Kreat
    0.41
    POSITIVE LOGITS
     haemorrh
    0.52
    数目
    0.51
     ansiedad
    0.48
    痉
    0.47
    定时
    0.47
     sintomi
    0.46
    гови
    0.45
     lés
    0.45
     etanol
    0.45
    骜
    0.45
    Activations Density 0.000%

    No Known Activations