© 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. 105802
    Prev
    Next
    INDEX
    Explanations

    classification trees

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

    roleplay style questions

    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
     conscient
    0.45
    感兴趣
    0.44
     ONLY
    0.43
     Session
    0.42
    shan
    0.41
    CHEN
    0.41
     Yin
    0.41
    t
    0.41
     formally
    0.40
     Indira
    0.40
    POSITIVE LOGITS
    穫
    0.51
    łat
    0.48
     kriminal
    0.48
     دفع
    0.46
    賭
    0.45
    適切
    0.45
     ಪೊಲೀಸ
    0.45
     nieruchomości
    0.45
    rescue
    0.44
    älj
    0.44
    Activations Density 0.001%

    No Known Activations