© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 47681
    Prev
    Next
    INDEX
    Explanations

    organizational information

    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
    ⵅ
    0.48
     faiblement
    0.46
    সভাপতি
    0.46
    inairement
    0.44
     제가
    0.44
    ալ
    0.43
    нього
    0.43
    валися
    0.43
    suivant
    0.43
     কয়েকটি
    0.42
    POSITIVE LOGITS
     a
    0.51
    0.51
     E
    0.49
    d
    0.48
     D
    0.47
    D
    0.45
     Seb
    0.45
     new
    0.45
     P
    0.44
     un
    0.44
    Activations Density 0.001%

    No Known Activations