© 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. 179686
    Prev
    Next
    INDEX
    Explanations

    data transfer and transmission

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

    conversational questions using "you"

    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
     betreff
    0.47
    虑
    0.45
    भाष
    0.44
    他们的
    0.43
     nhiễm
    0.43
    حة
    0.43
     montón
    0.43
     combinação
    0.43
    要知道
    0.42
    的问题
    0.42
    POSITIVE LOGITS
     dungeons
    0.49
     Catholicism
    0.48
     grotesque
    0.46
     ಪಕ್ಷ
    0.46
    as
    0.44
    ’
    0.44
    ामध्ये
    0.44
     highs
    0.43
    ாகவும்
    0.43
     dungeon
    0.43
    Activations Density 0.001%

    No Known Activations