© 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. 128723
    Prev
    Next
    INDEX
    Explanations

    longing to

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

    discussion stems from

    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
     μπορού
    0.47
    קה
    0.45
    罅
    0.44
     berken
    0.44
     სახელ
    0.42
    分辨率
    0.41
    રિ
    0.41
    DESCRIPTOR
    0.41
    КИ
    0.41
    KAL
    0.40
    POSITIVE LOGITS
     treats
    0.44
     apologizing
    0.43
     strives
    0.42
    ურთ
    0.41
     Treats
    0.41
     Gases
    0.41
    ಸ
    0.41
     всегда
    0.41
     sucks
    0.41
     codzien
    0.41
    Activations Density 0.002%

    No Known Activations