© 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. 30587
    Prev
    Next
    INDEX
    Explanations

    super review

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

    secret

    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
     zarówno
    0.36
     سایر
    0.35
     sowohl
    0.33
    และการ
    0.32
     بأن
    0.32
     ఇతర
    0.32
    🕍
    0.31
     عہد
    0.31
     zowel
    0.30
    <unused2039>
    0.30
    POSITIVE LOGITS
    ，
    0.38
     máquina
    0.36
    在这里
    0.34
    `,
    0.34
     siempre
    0.34
     Brownian
    0.32
     tắm
    0.32
    こういう
    0.32
    ၊
    0.31
    ،
    0.31
    Activations Density 0.000%

    No Known Activations