© 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. 151688
    Prev
    Next
    INDEX
    Explanations

    in the mood for

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

    feeling or issue

    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
    resources
    0.59
    he
    0.56
    чы
    0.51
    f
    0.51
    in
    0.51
    常に
    0.50
    ad
    0.50
    n
    0.48
    always
    0.48
    WITH
    0.48
    POSITIVE LOGITS
     উক্ত
    0.49
     অবশিষ্ট
    0.49
     ataupun
    0.48
     Beverage
    0.47
     wollte
    0.47
     reluct
    0.45
     efectuar
    0.45
     chcia
    0.45
     غادي
    0.44
     warrants
    0.44
    Activations Density 0.014%

    No Known Activations