© 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. 211369
    Prev
    Next
    INDEX
    Explanations

    URL components and separators

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

    offering alternative topics

    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
     )$
    0.45
     ल
    0.44
    1
    0.44
    4
    0.43
     with
    0.43
     flie
    0.42
     ਤਾਂ
    0.42
     )
    0.41
    டன்
    0.41
     ಸಂಗ
    0.41
    POSITIVE LOGITS
    hwa
    0.51
    ौल
    0.51
    onerror
    0.48
    iskup
    0.47
     Wins
    0.46
    iegel
    0.46
    aphore
    0.45
    ्रेट
    0.45
    ricane
    0.45
     Wizards
    0.45
    Activations Density 0.001%

    No Known Activations