© 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. 203687
    Prev
    Next
    INDEX
    Explanations

    emotional and descriptive concepts

    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
    字
    0.43
    6
    0.42
     Waltz
    0.41
     remains
    0.41
    рби
    0.41
    拉丁
    0.40
     fork
    0.40
    )
    0.40
    ield
    0.39
     aimed
    0.38
    POSITIVE LOGITS
     participação
    0.51
    ộng
    0.47
    cimentos
    0.46
    呿
    0.46
     diretor
    0.46
    Após
    0.46
    Texto
    0.46
    Excelente
    0.46
    मान
    0.45
     iluminación
    0.45
    Activations Density 0.003%

    No Known Activations