© 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
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4337
    Prev
    Next
    INDEX
    Explanations

    initial followed by word

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

    acronyms and abbreviations

    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
     clockRadius
    0.23
    禟
    0.21
    <unused24>
    0.21
    เร็จ
    0.21
     veineux
    0.21
    菪
    0.21
    Sholes
    0.21
    निश्ड
    0.21
    醫
    0.20
    <unused82>
    0.20
    POSITIVE LOGITS
    inn
    0.28
    url
    0.28
     U
    0.27
    ano
    0.27
    aus
    0.26
    ins
    0.26
    aling
    0.26
    uro
    0.26
     K
    0.25
    ura
    0.25
    Activations Density 0.300%

    No Known Activations