© 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. 30674
    Prev
    Next
    INDEX
    Explanations

    about job

    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
    ب
    0.61
    太空
    0.60
    Venue
    0.58
    Closed
    0.55
    Gabriel
    0.52
    স
    0.52
    圭
    0.52
    Insurance
    0.51
    The
    0.51
    Event
    0.50
    POSITIVE LOGITS
    _
    0.74
    ।
    0.66
    ra
    0.65
    ungen
    0.59
    ri
    0.57
    owa
    0.57
    ati
    0.55
    lari
    0.55
     but
    0.54
    lardan
    0.54
    Activations Density 0.000%

    No Known Activations