© 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. 38299
    Prev
    Next
    INDEX
    Explanations

    when you

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

    introduces a topic or condition

    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
     grouped
    0.46
     inhaled
    0.39
    𝗝
    0.39
     oldest
    0.38
    そもそも
    0.38
     حي
    0.38
     young
    0.38
     breathed
    0.38
    ុល
    0.38
     publicly
    0.38
    POSITIVE LOGITS
     waardoor
    0.45
     και
    0.44
    ukup
    0.43
    Karena
    0.43
    และ
    0.43
    리와
    0.43
     causando
    0.42
    浏
    0.41
     protéger
    0.41
    ২৯
    0.41
    Activations Density 0.000%

    No Known Activations