© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4518
    Prev
    Next
    INDEX
    Explanations

    policy, governance, custom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    bs
    0.94
     Barrow
    0.78
    bah
    0.77
     Bodrum
    0.76
     Bs
    0.75
     Aragón
    0.73
    ö
    0.72
    BH
    0.71
     Fontaine
    0.71
     Avalon
    0.71
    POSITIVE LOGITS
    ↵
    1.09
     yeast
    1.01
    meck
    1.01
     wik
    0.98
     throm
    0.97
     maíz
    0.95
     [['
    0.94
     /><
    0.94
     antibiotics
    0.94
    formatics
    0.94
    Activations Density 0.120%

    No Known Activations