© 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. 40-GEMMASCOPE-2-RES-65K
    7. 549
    Prev
    Next
    INDEX
    Explanations

    words often followed by specific endings

    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_40_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
    ،
    0.28
    、
    0.27
    0.25
    ，
    0.25
     are
    0.23
    ,
    0.23
     (
    0.21
     to
    0.21
    )
    0.20
    ।
    0.19
    POSITIVE LOGITS
    oretically
    0.24
    ající
    0.24
    <unused384>
    0.22
    <unused283>
    0.22
     Kogi
    0.22
    <unused311>
    0.22
    aternal
    0.22
    abhavena
    0.21
     स्वादिष्ट
    0.21
    <unused499>
    0.21
    Activations Density 0.360%

    No Known Activations