© 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. 143098
    Prev
    Next
    INDEX
    Explanations

    eyes, shirt, minute, culture, farm

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

    we appreciate

    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
    確実に
    0.46
     Чу
    0.46
    曦
    0.44
     langfrist
    0.44
    гле
    0.43
    Ти
    0.43
    ostat
    0.41
     satisfe
    0.41
    Чу
    0.41
    滿足
    0.41
    POSITIVE LOGITS
     centres
    0.46
    மணி
    0.43
     হইয়৷
    0.41
     Gardens
    0.41
     scams
    0.40
     Warhammer
    0.40
    ুল
    0.40
    olia
    0.39
     detailing
    0.39
     mafia
    0.39
    Activations Density 0.000%

    No Known Activations