© 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. 189884
    Prev
    Next
    INDEX
    Explanations

    after a period

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

    cost function

    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
     আলো
    0.43
     ?",
    0.41
     ,
    0.40
     including
    0.40
     ?,
    0.40
     interruptions
    0.39
     interruption
    0.39
     उल्लंघन
    0.38
    を除く
    0.38
    +,
    0.38
    POSITIVE LOGITS
     момент
    0.61
     tắc
    0.51
    푯
    0.51
    ॉफ्ट
    0.49
    Adorable
    0.49
    ו
    0.48
    те
    0.48
    то
    0.46
    ൭
    0.46
    <h3>
    0.46
    Activations Density 0.000%

    No Known Activations