© 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. 1710
    Prev
    Next
    INDEX
    Explanations

    only statements

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

    only

    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
    म
    0.32
    ר
    0.31
    ر
    0.29
    er
    0.29
    )।
    0.29
     এছাড়া
    0.28
     oscillations
    0.28
    )。
    0.28
    𝟬
    0.27
     anions
    0.27
    POSITIVE LOGITS
    </h2>
    0.27
     лишь
    0.24
    два
    0.23
    1
    0.22
    ird
    0.22
    нг
    0.22
    有一种
    0.21
    敢
    0.21
    限于
    0.21
    霹
    0.21
    Activations Density 0.263%

    No Known Activations