© 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. 16-GEMMASCOPE-2-RES-262K
    7. 119425
    Prev
    Next
    INDEX
    Explanations

    i'm not saying

    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_16_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
    МИ
    0.52
    氛
    0.52
    ša
    0.50
    issaient
    0.50
    בה
    0.50
    NewGuid
    0.48
    et
    0.48
    λε
    0.48
    ेशा
    0.48
    Чу
    0.48
    POSITIVE LOGITS
     On
    0.63
     Accordingly
    0.63
     It
    0.61
     In
    0.59
     From
    0.58
    d
    0.57
    with
    0.56
     Kors
    0.54
     on
    0.54
     Rede
    0.54
    Activations Density 0.000%

    No Known Activations