© 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. 203435
    Prev
    Next
    INDEX
    Explanations

    chased off by

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

    automotive and travel commonalities

    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
    "]
    0.48
     Loved
    0.48
    ')
    0.46
     限定
    0.44
    选举
    0.44
    าน
    0.43
    '){
    0.43
    ")]
    0.43
    anath
    0.43
    အပိုင်း
    0.42
    POSITIVE LOGITS
    onomous
    0.53
     diagnostics
    0.47
     কমল
    0.47
    őt
    0.47
     lý
    0.46
     fortes
    0.46
    way
    0.46
    ownership
    0.46
     samt
    0.46
     sonic
    0.46
    Activations Density 0.000%

    No Known Activations