© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51645
    Prev
    Next
    INDEX
    Explanations

    invitations and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ตอบ
    0.47
    𝔀
    0.42
    敷
    0.41
    responses
    0.40
     рассе
    0.40
     वत्स
    0.40
    ദ്ധ
    0.40
     répond
    0.40
     듣
    0.40
    ebel
    0.39
    POSITIVE LOGITS
     asking
    0.62
     proposing
    0.61
     mengajak
    0.60
     requesting
    0.59
     invasive
    0.59
     Asking
    0.57
     invitación
    0.57
     предложить
    0.56
     proposes
    0.55
     proposition
    0.55
    Activations Density 0.145%

    No Known Activations