© 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-262K
    7. 94241
    Prev
    Next
    INDEX
    Explanations

    privacy and control

    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
     रचा
    0.46
     новое
    0.45
    ę
    0.43
     νέ
    0.42
     orphaned
    0.42
    伸び
    0.41
     애
    0.41
    גד
    0.41
     დაკ
    0.41
    ᱙
    0.41
    POSITIVE LOGITS
     আওয়
    0.45
    齐全
    0.45
    အောင်
    0.44
     winery
    0.43
     Winery
    0.43
     feld
    0.42
     typ
    0.40
    ㈣
    0.40
     Sandro
    0.40
     المت
    0.40
    Activations Density 0.004%

    No Known Activations