© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 203510
    Prev
    Next
    INDEX
    Explanations

    text segments about access, boundaries, or time

    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
     случаи
    0.45
    おく
    0.44
    ન્
    0.43
    ERIAL
    0.40
    扮演
    0.40
    </tbody>
    0.40
    ERING
    0.40
    ณ
    0.40
    dataTable
    0.39
    ARIOS
    0.39
    POSITIVE LOGITS
     you
    0.50
     (
    0.44
     baguette
    0.43
     업체
    0.43
     vlas
    0.42
     Sake
    0.42
     bundle
    0.42
     barista
    0.42
     Baths
    0.42
     Grant
    0.41
    Activations Density 0.010%

    No Known Activations