© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133284
    Prev
    Next
    INDEX
    Explanations

    stale quickly, protected fields

    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_40_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
     cups
    0.44
    ombe
    0.43
    cups
    0.42
     `=`,
    0.40
    indungan
    0.39
    GetString
    0.38
    Strom
    0.38
     antennis
    0.37
    ঞ্জাম
    0.37
     lọc
    0.37
    POSITIVE LOGITS
     MAM
    0.38
    Styles
    0.38
     chameleon
    0.38
     lev
    0.37
     mommy
    0.37
     Dain
    0.37
     CGPoint
    0.37
     kad
    0.36
     레
    0.36
    interested
    0.36
    Activations Density 0.001%

    No Known Activations