© 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. 86849
    Prev
    Next
    INDEX
    Explanations

    initials followed by punctuation

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

    individual liberties and everything

    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
    গ্রন্থ
    0.48
     stones
    0.47
     piedras
    0.46
    irittura
    0.45
    phases
    0.45
     hải
    0.44
     pierres
    0.44
    >×</
    0.44
     truy
    0.42
     আগ্রহ
    0.42
    POSITIVE LOGITS
     Ο
    0.45
     &/
    0.43
     CONTAINER
    0.40
     HOM
    0.40
    Ο
    0.40
    ฝ่าย
    0.39
    HON
    0.39
     DIRECTOR
    0.39
    ės
    0.39
     कंटे
    0.39
    Activations Density 0.000%

    No Known Activations