© 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. 93480
    Prev
    Next
    INDEX
    Explanations

    niche

    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
    삼성
    0.49
    DI
    0.45
    این
    0.45
    स्टर
    0.44
    ଚ
    0.44
    transformed
    0.44
    کر
    0.43
    Así
    0.42
     ഇത്തരം
    0.42
    խ
    0.41
    POSITIVE LOGITS
    _
    0.53
     capitol
    0.49
     Jungle
    0.46
     اله
    0.46
     temp
    0.46
     Viol
    0.45
     tempo
    0.45
     jungle
    0.45
    tempo
    0.44
     Capital
    0.44
    Activations Density 0.001%

    No Known Activations