© 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. 58165
    Prev
    Next
    INDEX
    Explanations

    the noun following the

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

    buy six

    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
    K
    0.48
    PersonalInfo
    0.48
    េ
    0.47
     письмо
    0.47
     главное
    0.46
    ا
    0.46
    題目
    0.46
     Kasım
    0.46
    ﺱ
    0.45
    െ
    0.45
    POSITIVE LOGITS
    animate
    0.45
     ascribed
    0.43
     exorbit
    0.41
    ioi
    0.41
     इनमें
    0.40
     estoque
    0.40
     atrib
    0.40
    cloudinary
    0.39
    illae
    0.39
    🏿
    0.39
    Activations Density 0.000%

    No Known Activations