© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 250
    Prev
    Next
    INDEX
    Explanations

    Urano

    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_31_width_16k_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
    ্ের
    0.25
     coerce
    0.23
    ینګ
    0.22
    倸
    0.22
     interpolated
    0.21
     QRCode
    0.21
    原子炉
    0.21
     agente
    0.21
    িকারী
    0.20
    प्लीट
    0.20
    POSITIVE LOGITS
    -
    0.30
    و
    0.26
    <0xEE>
    0.24
    ー
    0.22
    <0xF0>
    0.22
    ’
    0.22
    '
    0.22
    ್
    0.22
    ֹ
    0.21
    жан
    0.21
    Activations Density 2.909%

    No Known Activations