© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49990
    Prev
    Next
    INDEX
    Explanations

    setting and role descriptions

    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
    NT
    0.41
    bookmark
    0.40
    ್ಟ
    0.38
    James
    0.38
     NTT
    0.37
     குறித்து
    0.36
    麂
    0.36
    nt
    0.35
     NT
    0.35
    speaker
    0.35
    POSITIVE LOGITS
     whom
    0.65
     الذين
    0.57
    whom
    0.56
     którzy
    0.52
     ktorí
    0.52
     who
    0.51
     whose
    0.50
     cuya
    0.50
     cuyas
    0.49
     kteří
    0.49
    Activations Density 0.049%

    No Known Activations