© 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. 33201
    Prev
    Next
    INDEX
    Explanations

    grammatical features or states

    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
    IDO
    0.47
    льник
    0.44
    Ordenar
    0.43
     Beitrag
    0.43
    Тре
    0.42
    льзу
    0.41
    Ꮞ
    0.41
    élite
    0.41
    恂
    0.41
     своим
    0.40
    POSITIVE LOGITS
    bí
    0.38
     conversational
    0.37
    ots
    0.37
     tantamount
    0.37
     determ
    0.37
     entire
    0.37
     spelling
    0.36
     lavender
    0.35
     tearing
    0.35
     Furthermore
    0.35
    Activations Density 0.001%

    No Known Activations