© 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. 110880
    Prev
    Next
    INDEX
    Explanations

    pets, column vector, appreciate

    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
     snapshot
    0.47
     جانے
    0.43
    ኼ
    0.41
     Bedarf
    0.41
     q
    0.40
     যাবেন
    0.40
     folks
    0.40
     forward
    0.39
     adelante
    0.39
    ທີ
    0.39
    POSITIVE LOGITS
    Ι
    0.53
    िट
    0.50
    Tight
    0.50
    s
    0.49
    ছাড়া
    0.48
     ผ
    0.47
     Tight
    0.47
    Ό
    0.47
     שלך
    0.46
    摟
    0.46
    Activations Density 0.000%

    No Known Activations