© 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. 232853
    Prev
    Next
    INDEX
    Explanations

    "have" followed by punctuation or a noun

    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
    哂
    0.44
    蟎
    0.43
     була
    0.43
    因
    0.43
    ತ
    0.42
    ガン
    0.42
    дә
    0.41
    知
    0.41
    halo
    0.40
    信
    0.40
    POSITIVE LOGITS
     ejecutar
    0.49
     atacar
    0.48
     manej
    0.46
     Nana
    0.45
     manejar
    0.44
     wykony
    0.44
     oito
    0.43
     escrever
    0.43
     trabalh
    0.42
     localizar
    0.42
    Activations Density 0.000%

    No Known Activations