© 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. 16-GEMMASCOPE-2-RES-16K
    7. 489
    Prev
    Next
    INDEX
    Explanations

    numbers and units of measurement

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

    1 followed by 6 or 2

    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_16_width_16k_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
    6
    0.41
    ですが
    0.40
    ৪
    0.40
    ون
    0.39
    5
    0.37
    ното
    0.36
    ৫
    0.36
    ৬
    0.36
    4
    0.35
    3
    0.34
    POSITIVE LOGITS
     it
    0.40
     to
    0.39
     You
    0.38
     you
    0.36
     your
    0.34
     a
    0.34
     It
    0.34
    It
    0.32
    Phones
    0.32
    Email
    0.31
    Activations Density 0.521%

    No Known Activations