© 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. 31-GEMMASCOPE-2-RES-262K
    7. 12050
    Prev
    Next
    INDEX
    Explanations

    entity on platform

    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
    বার
    0.38
     weniger
    0.37
    菂
    0.35
     يوم
    0.34
     mindre
    0.34
    と同様
    0.34
     jaja
    0.34
    昍
    0.34
     हद
    0.34
     wenige
    0.33
    POSITIVE LOGITS
     پھر
    0.37
    নীয়
    0.34
     Neem
    0.33
    itee
    0.32
    YouTube
    0.32
     Nath
    0.32
     whol
    0.32
     Sha
    0.32
    Gmail
    0.32
     deserves
    0.31
    Activations Density 0.000%

    No Known Activations