© 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. 52027
    Prev
    Next
    INDEX
    Explanations

    roles and key nouns

    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
    вет
    0.54
    고
    0.53
    dangerous
    0.51
    ப்பும்
    0.50
    ﺓ
    0.49
    iyal
    0.49
     शत्र
    0.49
    ཧ
    0.49
    tet
    0.48
    B
    0.47
    POSITIVE LOGITS
     dei
    0.51
    oski
    0.50
     Verständ
    0.48
     sätt
    0.47
     lapp
    0.46
     måde
    0.44
     cib
    0.44
     pane
    0.43
     equilib
    0.43
     liber
    0.43
    Activations Density 0.007%

    No Known Activations