© 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. 39837
    Prev
    Next
    INDEX
    Explanations

    easy to install

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

    personal experiences and outcomes

    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
     خواهد
    0.45
     doubtless
    0.44
     คง
    0.44
    (".
    0.43
    виа
    0.42
    ИН
    0.41
    뵙
    0.41
     certamente
    0.40
    のでしょう
    0.39
    며
    0.39
    POSITIVE LOGITS
     resultó
    0.55
     потребо
    0.54
    took
    0.51
     took
    0.51
     resulted
    0.50
     recomand
    0.48
     anbef
    0.48
     оказалось
    0.47
     recomiendo
    0.47
     Puedes
    0.46
    Activations Density 0.083%

    No Known Activations