© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 51
    Prev
    Next
    INDEX
    Explanations

    forty

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

    numbers and ranges

    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
     ১৩২২
    0.54
     बताना
    0.47
    楇
    0.47
    য়াত
    0.46
     innumerable
    0.45
     १९
    0.45
    ീകരിച്ച
    0.45
     ನಿಮ್ಮ
    0.44
     pozn
    0.43
    ნიშვნ
    0.43
    POSITIVE LOGITS
    0
    1.37
    5
    1.17
     puluh
    1.10
    8
    1.01
    6
    0.99
    9
    0.95
    3
    0.93
    десят
    0.92
    7
    0.91
    4
    0.90
    Activations Density 1.004%

    No Known Activations