© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5250
    Prev
    Next
    INDEX
    Explanations

    billions and millions of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ون
    0.74
    आई
    0.70
    as
    0.70
     cuddle
    0.68
    پ
    0.68
    ي
    0.67
     as
    0.66
     tonnage
    0.64
     megawatts
    0.62
     equipes
    0.62
    POSITIVE LOGITS
    <h2>
    0.68
    }
    0.63
    </th>
    0.59
    </h2>
    0.57
     लोगों
    0.55
     people
    0.55
     Menschen
    0.55
    </b>
    0.53
    esta
    0.53
    คน
    0.52
    Activations Density 0.013%

    No Known Activations