© 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. 45987
    Prev
    Next
    INDEX
    Explanations

    membership, timeframe, club

    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
     economists
    0.43
     econometric
    0.41
     populist
    0.40
    ?
    0.40
    👿
    0.40
     mysteriously
    0.39
     indignation
    0.39
    factory
    0.39
     venido
    0.39
     debunk
    0.39
    POSITIVE LOGITS
    罨
    0.51
     பாதுகாப்பு
    0.46
     สามารถ
    0.45
    翛
    0.45
     подразуме
    0.45
    สามารถ
    0.44
    īs
    0.42
    膂
    0.41
     równ
    0.41
    ามารถ
    0.41
    Activations Density 0.022%

    No Known Activations