© 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. 212758
    Prev
    Next
    INDEX
    Explanations

    latest tweets

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

    introducing explanations or specifics

    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
     affaires
    0.47
    ueva
    0.44
    3
    0.43
     utter
    0.42
     করিলে
    0.41
     of
    0.41
     sujet
    0.40
    봅시다
    0.40
    tert
    0.39
    riert
    0.39
    POSITIVE LOGITS
    ا
    0.58
    ሎች
    0.54
    originally
    0.51
    ід
    0.51
     ਜਾਣ
    0.50
    кли
    0.50
    ामध्ये
    0.49
    ар
    0.49
    ائب
    0.49
    вед
    0.47
    Activations Density 0.000%

    No Known Activations