© 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. 42861
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives followed by nouns

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

    interrupting planting stomach after quickly

    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
    仳
    0.47
    に関
    0.46
     destabil
    0.45
    versed
    0.45
    ὀ
    0.44
    Kart
    0.43
    ダス
    0.43
    Lic
    0.43
    证券投资基金
    0.43
     অবকাঠ
    0.42
    POSITIVE LOGITS
     singers
    0.52
     مين
    0.52
     สาว
    0.51
     画
    0.51
     leggi
    0.50
     ges
    0.49
     dva
    0.49
     veck
    0.48
     kto
    0.48
     എല്ലാവ
    0.48
    Activations Density 0.000%

    No Known Activations