© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13282
    Prev
    Next
    INDEX
    Explanations

    say "manner" or "way"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    길
    0.56
     डेर
    0.52
    档案馆
    0.52
     পথ
    0.52
    すごい
    0.50
     درباره
    0.50
    睞
    0.49
    大事
    0.49
    ведение
    0.49
     зарубе
    0.49
    POSITIVE LOGITS
     manner
    3.95
    manner
    3.66
     Manner
    3.20
     fashion
    2.81
     manners
    2.73
    fashion
    2.39
     Fashion
    2.20
    Fashion
    2.20
     maniera
    2.17
     fashions
    2.06
    Activations Density 0.056%

    No Known Activations