© 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. 207949
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    firm, nudge, remind, monkey, kill

    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
     GameOver
    0.50
    聚集
    0.49
     MessageBox
    0.44
    湖
    0.44
    areader
    0.43
     wading
    0.42
    чам
    0.42
    ಯೇ
    0.41
     博文
    0.41
     సంగ
    0.40
    POSITIVE LOGITS
     sophistic
    0.52
    ítés
    0.51
    د
    0.50
    𝚜
    0.50
    innen
    0.50
    Für
    0.48
    Solic
    0.47
     strengthened
    0.47
     verstär
    0.47
    Eine
    0.47
    Activations Density 0.000%

    No Known Activations