© 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. 4523
    Prev
    Next
    INDEX
    Explanations

    word beginnings

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

    closing parentheses and brackets

    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
    Â
    0.53
    â
    0.52
    <sub>
    0.50
    ٬
    0.49
    <sup>
    0.49
    Ã
    0.49
    _<
    0.46
    âl
    0.46
    ��������
    0.45
    ã
    0.44
    POSITIVE LOGITS
    🐽
    0.40
    🐕
    0.40
     ==============
    0.39
    㗆
    0.39
     ===============
    0.37
     -------------
    0.36
     UserRepository
    0.36
    🍄
    0.36
    💂
    0.36
     을
    0.36
    Activations Density 0.004%

    No Known Activations