© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75973
    Prev
    Next
    INDEX
    Explanations

    trends and changes

    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
     ყ
    0.46
     запя
    0.45
    چر
    0.43
    叵
    0.43
     afin
    0.42
    リエ
    0.42
    ﭼ
    0.41
    、
    0.40
     persec
    0.40
    ศี
    0.40
    POSITIVE LOGITS
    p
    0.43
     concert
    0.43
    rupted
    0.42
     classes
    0.42
     effects
    0.41
    dem
    0.41
    gly
    0.41
    apshot
    0.40
    clust
    0.40
    adım
    0.40
    Activations Density 0.000%

    No Known Activations