© 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. 40716
    Prev
    Next
    INDEX
    Explanations

    limited liability or poor contrast

    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
    or
    0.49
    بی
    0.47
     commonly
    0.44
     seals
    0.43
    یند
    0.42
    0
    0.42
    Cel
    0.42
    ren
    0.41
     soldered
    0.41
    ă
    0.41
    POSITIVE LOGITS
    তত্ব
    0.55
     управления
    0.50
     ममता
    0.50
     目前
    0.48
     кушымта
    0.48
    
    0.48
     pohon
    0.47
    只有
    0.47
    ด้อ
    0.45
    തിന്റെ
    0.45
    Activations Density 0.007%

    No Known Activations