© 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. 38132
    Prev
    Next
    INDEX
    Explanations

    continuously learn vs static

    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
     شیمی
    0.49
     Αυ
    0.45
     আহ্বান
    0.45
     ე
    0.45
     एकता
    0.44
     پیم
    0.43
    Ï
    0.43
    ><
    0.43
     Amnesty
    0.42
     افراد
    0.42
    POSITIVE LOGITS
    ্স
    0.47
     circula
    0.45
    多的
    0.44
    ركه
    0.44
     multiplica
    0.43
    傳
    0.43
    는데
    0.42
     gaping
    0.41
    anjang
    0.41
     Malaga
    0.40
    Activations Density 0.002%

    No Known Activations