© 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. 48906
    Prev
    Next
    INDEX
    Explanations

    Buckeye Trail, running of

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

    contrasting ideas with but/while

    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
    ш
    0.50
     comparatively
    0.47
     međ
    0.47
     dakkh
    0.47
     stille
    0.47
     ဒီ
    0.44
    кти
    0.44
    ស
    0.44
     decomp
    0.44
     fier
    0.43
    POSITIVE LOGITS
    <unused80>
    0.45
     जाएंगी
    0.44
    锂
    0.44
     달리
    0.43
    ວດ
    0.43
    工夫
    0.43
     आपल्याला
    0.42
    Estas
    0.42
    คุณ
    0.42
    onso
    0.42
    Activations Density 0.000%

    No Known Activations