© 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. 91458
    Prev
    Next
    INDEX
    Explanations

    €, API, exported, handle, complex

    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
    is
    0.50
     Kakkar
    0.47
    Area
    0.46
     Toss
    0.46
    TouchUpInside
    0.43
    رد
    0.43
     رب
    0.43
    ،
    0.43
    শ্বর
    0.42
    权限
    0.42
    POSITIVE LOGITS
     수출
    0.50
     SupCt
    0.48
     stoichi
    0.47
     trat
    0.46
     LaF
    0.46
     exported
    0.42
     asem
    0.42
     AppMethodBeat
    0.42
     metastable
    0.41
     funcionar
    0.41
    Activations Density 0.005%

    No Known Activations