© 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. 184428
    Prev
    Next
    INDEX
    Explanations

    networking protocol

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

    asking academic questions

    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
    ලු
    0.51
    ستي
    0.47
    HCM
    0.46
    రూ
    0.44
    亜
    0.44
    ଖ
    0.44
     ガラス
    0.44
    𝐛
    0.44
     oats
    0.43
    ло
    0.43
    POSITIVE LOGITS
     mendorong
    0.54
    tevõ
    0.51
     erud
    0.47
     Uncomment
    0.47
     discour
    0.46
     protagonist
    0.46
     dignit
    0.45
     récomp
    0.45
     culturales
    0.44
     guvern
    0.44
    Activations Density 0.000%

    No Known Activations