© 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. 126623
    Prev
    Next
    INDEX
    Explanations

    other things equal

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

    prologue, the story, quarter cup

    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
    ।
    0.61
    ‬
    0.51
    <0x0D>
    0.51
    ↵
    0.49
    Ő
    0.49
    </u>
    0.49
     à
    0.47
    </h4>
    0.47
    ʕ
    0.46
     bellow
    0.46
    POSITIVE LOGITS
     套
    0.52
     스테
    0.49
     сли
    0.47
     તેણીએ
    0.47
    angsa
    0.45
     તેણી
    0.45
    েন্দু
    0.45
    랜드
    0.44
    隐含规则
    0.44
    리티
    0.43
    Activations Density 0.003%

    No Known Activations