© 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. 33176
    Prev
    Next
    INDEX
    Explanations

    building your email list

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

    Hagia Sophia, definition, dependencies, loving God, loop

    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
    пления
    0.49
     торже
    0.49
    いの
    0.48
     ૩
    0.47
    ͤ
    0.47
    ૧
    0.46
     lze
    0.45
    镌
    0.44
     বিস্তৃত
    0.44
     архівної
    0.44
    POSITIVE LOGITS
    n
    0.53
    Faction
    0.50
    Nodo
    0.47
    ad
    0.45
    BAD
    0.45
    onen
    0.45
    isah
    0.45
    Programme
    0.45
    mixer
    0.44
    Offering
    0.44
    Activations Density 0.000%

    No Known Activations