© 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. 8550
    Prev
    Next
    INDEX
    Explanations

    phrases and varied languages

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

    concepts and their roles

    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
    在
    0.58
    ک
    0.54
    P
    0.49
    J
    0.49
    ],
    0.48
     staffers
    0.48
    "
    0.47
     masquer
    0.47
     challengers
    0.47
    L
    0.47
    POSITIVE LOGITS
     rivière
    0.55
     дър
    0.49
     ге
    0.48
     phrase
    0.47
    ূতন
    0.47
     faci
    0.46
     прошло
    0.46
     hilly
    0.46
     понятие
    0.46
    hluk
    0.45
    Activations Density 0.000%

    No Known Activations