© 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. 69944
    Prev
    Next
    INDEX
    Explanations

    words and numbers

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

    joint filing

    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
     mentales
    0.48
    iliency
    0.46
     ਦ
    0.46
    ambers
    0.45
    bss
    0.45
     पहुंचाया
    0.45
     보도록
    0.45
    angkap
    0.44
    uts
    0.44
    Colors
    0.44
    POSITIVE LOGITS
    ৩
    0.46
     not
    0.44
    သင့်
    0.43
     Tüm
    0.43
     dry
    0.42
    ২
    0.42
    ღ
    0.42
    방법
    0.41
     trường
    0.41
     இதற்கு
    0.41
    Activations Density 0.000%

    No Known Activations