© 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. 31122
    Prev
    Next
    INDEX
    Explanations

    option, skills, face, expiration, mechanics, samples, this

    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
     торже
    0.47
     聞い
    0.46
    ats
    0.44
     уены
    0.42
    ációs
    0.41
     &$\
    0.41
    ública
    0.41
     ప్రత్యేక
    0.41
     符合
    0.39
    andte
    0.39
    POSITIVE LOGITS
     enduro
    0.50
     diga
    0.50
     volv
    0.47
     contr
    0.47
    بر
    0.46
     afer
    0.46
     endocr
    0.46
    ث
    0.46
     End
    0.46
     inicial
    0.46
    Activations Density 0.023%

    No Known Activations