© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41123
    Prev
    Next
    INDEX
    Explanations

    temporarily, now, data, mainly, out

    np_acts-logits-general · gemini-2.5-flash-lite

    defines or approximates conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     olmadan
    0.51
    uriken
    0.46
    itih
    0.46
     मल्टीप्लाई
    0.44
     Саме
    0.44
     сложных
    0.44
     वरना
    0.44
    舴
    0.44
    ogg
    0.44
    YD
    0.43
    POSITIVE LOGITS
    صور
    0.44
    邨
    0.41
    সন্ধ
    0.39
    장은
    0.38
    \
    0.38
     þat
    0.38
    总经理
    0.37
     IHC
    0.37
     immunity
    0.37
     CNC
    0.37
    Activations Density 0.000%

    No Known Activations