© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205439
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their common continuations

    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
    н
    0.61
    n
    0.54
    as
    0.52
    িয়াই
    0.49
    ن
    0.48
    始め
    0.47
     intersections
    0.47
    т
    0.47
     intersect
    0.47
     owned
    0.46
    POSITIVE LOGITS
    Открыть
    0.49
    )`,
    0.48
    methylsulfanyl
    0.46
    `,
    0.45
    ChoiceItemLayout
    0.45
    }`}>
    0.45
    cssMode
    0.45
    ել
    0.44
    えました
    0.44
    anggilan
    0.43
    Activations Density 0.000%

    No Known Activations