© 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. 42174
    Prev
    Next
    INDEX
    Explanations

    This is

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

    token to word conversions

    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
    ཟ
    0.44
    த்தா
    0.41
    зви
    0.40
     CFC
    0.40
     deple
    0.40
    禇
    0.40
    鉢
    0.39
    <u>
    0.38
    லில்
    0.38
     ரா
    0.38
    POSITIVE LOGITS
    نګه
    0.54
     iremos
    0.54
     sylvis
    0.52
     podemos
    0.50
     podremos
    0.49
     buckles
    0.49
    我們可以
    0.49
     کنیم
    0.48
    我们会
    0.48
     ကျွန်
    0.48
    Activations Density 0.000%

    No Known Activations