© 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. 47558
    Prev
    Next
    INDEX
    Explanations

    Pope John Paul II

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

    explanation breakdown

    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
     центру
    0.53
    センター
    0.51
     центр
    0.51
    壮
    0.46
     центре
    0.45
    ミス
    0.45
     быстрее
    0.44
     истины
    0.44
     ጎ
    0.43
    または
    0.43
    POSITIVE LOGITS
     totalled
    0.46
     fotograf
    0.45
     leto
    0.42
    zipped
    0.42
     totaled
    0.41
    idmat
    0.41
     partecipanti
    0.40
    }\,
    0.40
     ricev
    0.40
     detta
    0.39
    Activations Density 0.000%

    No Known Activations