© 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. 27953
    Prev
    Next
    INDEX
    Explanations

    lists connected by and

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

    words ending in 'ad' or 'os'

    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
    ،
    1.03
    ,
    0.98
    ，
    0.91
    *,
    0.84
    ၊
    0.83
    、
    0.82
    ፣
    0.78
    -,
    0.77
    ‌,
    0.75
    %,
    0.75
    POSITIVE LOGITS
     आणि
    0.69
     અને
    0.60
     ਅਤੇ
    0.59
    度和
    0.55
    力和
    0.53
     និង
    0.52
     uye
    0.51
     ಮತ್ತು
    0.50
     and
    0.50
    性和
    0.50
    Activations Density 0.134%

    No Known Activations