© 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. 11349
    Prev
    Next
    INDEX
    Explanations

    non-ascii characters

    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
     Krishnam
    0.44
    ienced
    0.43
     சு
    0.41
    реди
    0.41
     επισ
    0.40
    母亲
    0.40
    谊
    0.40
     सेमेस्टर
    0.40
    长期
    0.40
    үнд
    0.40
    POSITIVE LOGITS
     ¨
    0.50
    ¯
    0.47
     alguna
    0.44
     alors
    0.44
     verzi
    0.44
     schon
    0.44
     allerede
    0.43
     oligos
    0.43
     allerlei
    0.43
     arbre
    0.42
    Activations Density 0.008%

    No Known Activations