© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 44960
    Prev
    Next
    INDEX
    Explanations

    content warning

    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
     उर्वर
    0.46
    underbrace
    0.43
    ̓
    0.40
    干燥
    0.40
     forfe
    0.40
     আদৌ
    0.40
    omers
    0.38
    space
    0.38
    urization
    0.38
     ಖರೀದ
    0.38
    POSITIVE LOGITS
    എസ്
    0.49
    cción
    0.46
     চাহিল
    0.46
    𝖽
    0.46
    枫
    0.43
    ᄃ
    0.43
    Со
    0.42
     çağ
    0.42
     aluno
    0.42
    디오
    0.41
    Activations Density 0.003%

    No Known Activations