© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94232
    Prev
    Next
    INDEX
    Explanations

    decision

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

    niche and brand engagement

    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
    Negative Logits
     Compress
    0.45
    紝
    0.45
     Букмекердик
    0.44
     নিয়ম
    0.44
    選
    0.44
    ège
    0.43
     Марафон
    0.43
    跟他
    0.43
     너무
    0.43
     કેટ
    0.43
    POSITIVE LOGITS
     parties
    0.54
    ×
    0.53
    rof
    0.50
     effectu
    0.49
     casas
    0.47
     sanctuaries
    0.46
     терапии
    0.45
    :
    0.45
     возраста
    0.45
     места
    0.44
    Activations Density 0.000%

    No Known Activations