© 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. 191857
    Prev
    Next
    INDEX
    Explanations

    winner or loser

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

    percentages and prevalence

    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
     ],
    0.51
     voitures
    0.47
    plers
    0.45
    ],
    0.45
     गाड़ियों
    0.44
    ₁,
    0.43
    ]]),
    0.42
     ruso
    0.42
     “,
    0.42
     قوانین
    0.41
    POSITIVE LOGITS
    人为
    0.46
    连忙
    0.46
    补
    0.44
    แต่
    0.43
    私募
    0.43
    するように
    0.43
     Chong
    0.42
    ของเรา
    0.42
    但不
    0.42
    处于
    0.42
    Activations Density 0.001%

    No Known Activations