© 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-262K
    7. 92562
    Prev
    Next
    INDEX
    Explanations

    don't or shouldn't

    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_262k_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
     ನೀವು
    0.58
     நீங்கள்
    0.56
     તમે
    0.55
     നിങ്ങളുടെ
    0.55
     あなた
    0.55
     ನಿಮ್ಮ
    0.53
     時
    0.52
     შეგი
    0.51
     zmniejs
    0.50
     より
    0.50
    POSITIVE LOGITS
    ,
    0.48
     manpower
    0.47
     owned
    0.43
     pol
    0.42
     Dix
    0.42
     sum
    0.42
     Plano
    0.41
     design
    0.41
     staff
    0.41
     marinated
    0.41
    Activations Density 0.003%

    No Known Activations