© 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. 189142
    Prev
    Next
    INDEX
    Explanations

    page, subject, year, reproduce

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

    jokes about women

    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
     defiance
    0.47
    ᕙ
    0.44
    波動
    0.43
    ფილი
    0.43
     مبت
    0.42
    STRING
    0.42
    bos
    0.41
    freedom
    0.41
    ดำเนิน
    0.41
     شخصیت
    0.40
    POSITIVE LOGITS
     அறிகுற
    0.53
     of
    0.51
    鲔
    0.50
     Applicant
    0.45
    鲐
    0.45
    ства
    0.44
    च्‍
    0.44
    ícia
    0.44
     মহামার
    0.43
     torso
    0.43
    Activations Density 0.001%

    No Known Activations