© 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. 187052
    Prev
    Next
    INDEX
    Explanations

    destroyed. got twin. without using. enough! dresses

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

    deter potential, relying on

    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
    topnav
    0.50
     竹
    0.49
     計算
    0.46
    ंपूर्वी
    0.46
    ეთის
    0.45
     Οι
    0.45
    巔
    0.45
    ोहित
    0.44
     Criteria
    0.44
     Αν
    0.44
    POSITIVE LOGITS
     başlayalım
    0.45
    Blow
    0.43
    <h1>
    0.41
    Rotate
    0.41
    到时候
    0.41
     aggravate
    0.40
    [-\
    0.40
    应当
    0.40
    万
    0.40
    [:
    0.40
    Activations Density 0.000%

    No Known Activations