© 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-65K
    7. 30209
    Prev
    Next
    INDEX
    Explanations

    quantifiable results and data

    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_65k_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
     সংগঠন
    0.51
    ជាតិ
    0.50
     एकदम
    0.48
    되는
    0.48
    လည်း
    0.48
     నాలు
    0.46
     부분이
    0.46
    練
    0.46
     subTest
    0.46
     actresses
    0.45
    POSITIVE LOGITS
    ie
    0.46
    chamber
    0.42
    ib
    0.41
     keeps
    0.40
    гиз
    0.40
     GI
    0.40
     والب
    0.40
     mesure
    0.39
    abd
    0.39
     cares
    0.39
    Activations Density 0.003%

    No Known Activations