© 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. 81632
    Prev
    Next
    INDEX
    Explanations

    file or filepath operations

    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
    ომ
    0.56
    ācijas
    0.53
    압
    0.53
     Jehová
    0.52
    ціона
    0.52
    스
    0.51
    년
    0.50
    ів
    0.50
     chuyển
    0.50
    ўным
    0.50
    POSITIVE LOGITS
     dabei
    0.49
     t
    0.45
     ras
    0.45
     vigil
    0.44
     supermarket
    0.44
    Num
    0.43
     supervised
    0.42
     cafeteria
    0.42
    AR
    0.42
     machine
    0.42
    Activations Density 0.000%

    No Known Activations