© 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. 31343
    Prev
    Next
    INDEX
    Explanations

    full text of

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

    fullness and truth

    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
     معلومات
    0.45
     informace
    0.41
     собстве
    0.40
     собствен
    0.40
     ინფორმა
    0.40
     logika
    0.40
    smittel
    0.39
    掌
    0.39
    ssä
    0.39
    逻辑
    0.38
    POSITIVE LOGITS
    FULL
    0.53
    full
    0.47
    adona
    0.45
    Full
    0.44
     полно
    0.42
    لیس
    0.41
    ilda
    0.40
    fda
    0.40
    realpath
    0.39
    itoti
    0.39
    Activations Density 0.031%

    No Known Activations