© 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. 64294
    Prev
    Next
    INDEX
    Explanations

    fractions and measurements

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

    mathematical equations

    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
     слу
    0.50
    \|
    0.46
    范
    0.44
    ')
    0.44
    ినీ
    0.43
    iguo
    0.43
    \]
    0.42
    𝙴
    0.41
    ᵢ
    0.41
    /')
    0.41
    POSITIVE LOGITS
    ا
    0.52
    اگ
    0.46
    اپ
    0.45
    調整
    0.44
    اا
    0.43
    اش
    0.43
     adjuster
    0.43
    istä
    0.41
    اج
    0.41
    措置
    0.41
    Activations Density 0.010%

    No Known Activations