© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5602
    Prev
    Next
    INDEX
    Explanations

    word endings -ase, -ose, -se

    np_acts-logits-general · gemini-2.5-flash-lite

    concise / conciseness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    徇
    0.46
    ropa
    0.46
    িলিয়া
    0.46
    侸
    0.43
    প্রচার
    0.42
    㹮
    0.42
    ]+"
    0.39
    䡓
    0.39
     feria
    0.39
    য়াত
    0.39
    POSITIVE LOGITS
    se
    2.22
    ase
    1.95
    SE
    1.93
    се
    1.77
    ese
    1.76
    ose
    1.75
    ASE
    1.74
    ise
    1.69
    nse
    1.64
    せ
    1.62
    Activations Density 0.143%

    No Known Activations