© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8164
    Prev
    Next
    INDEX
    Explanations

    pi and multiplication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused342>
    0.46
    <unused981>
    0.45
    <unused743>
    0.43
    Glor
    0.42
     тонн
    0.42
     Или
    0.41
    ecek
    0.41
    <unused603>
    0.41
    бург
    0.41
     дре
    0.40
    POSITIVE LOGITS
     adicional
    0.50
    による
    0.40
     doing
    0.40
    (
    0.38
     people
    0.37
     struggling
    0.37
     repetition
    0.37
    \
    0.36
     normal
    0.36
     operator
    0.36
    Activations Density 0.161%

    No Known Activations