© 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. 126899
    Prev
    Next
    INDEX
    Explanations

    actions following specific entities

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

    qualities and evaluations

    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
     varied
    0.61
    闾
    0.47
    ơm
    0.45
     excitement
    0.45
    𝘔
    0.45
     vary
    0.43
     welcoming
    0.43
     ponies
    0.43
     abit
    0.43
    Между
    0.43
    POSITIVE LOGITS
     mengatakan
    0.45
     দারিদ্র
    0.42
     বলেছেন
    0.42
    ovsky
    0.42
     జట్టు
    0.42
     blaming
    0.41
     Uncomment
    0.41
    ).
    0.41
    ].
    0.41
    てください
    0.40
    Activations Density 0.001%

    No Known Activations