© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 4130
    Prev
    Next
    INDEX
    Explanations

    specific entities and 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_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
     Gómez
    0.19
     جارہ
    0.17
     سبسڈی
    0.17
     Grafik
    0.17
     س
    0.17
     například
    0.16
     dépenses
    0.16
    ങ്ങൾക്ക്
    0.16
    سازی
    0.16
     الغذ
    0.16
    POSITIVE LOGITS
    ES
    0.20
    eslint
    0.20
    ଂ
    0.20
    ion
    0.20
    ನ್
    0.18
     встречи
    0.18
    傳統
    0.18
    WITH
    0.18
    και
    0.18
     анти
    0.18
    Activations Density 1.265%

    No Known Activations