© 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-65K
    7. 5173
    Prev
    Next
    INDEX
    Explanations

    San and al names

    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
    s
    0.46
    8
    0.44
     vasomotor
    0.43
    ים
    0.43
     salaried
    0.43
     authorised
    0.43
    6
    0.41
    9
    0.41
    上
    0.39
    روج
    0.38
    POSITIVE LOGITS
    0.48
     భాగంగా
    0.46
     स्टोरेज
    0.44
     St
    0.43
     нього
    0.43
     точке
    0.42
     Mexique
    0.42
     този
    0.40
    馇
    0.40
    膑
    0.40
    Activations Density 0.014%

    No Known Activations