© 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. 53-GEMMASCOPE-2-RES-65K
    7. 770
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    Create a, way to

    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
     ২২
    0.71
    ২২
    0.60
    <0xB9>
    0.56
    十二
    0.50
    <unused82>
    0.49
    十八
    0.47
    された
    0.47
     Уже
    0.46
     alkyl
    0.46
     eighteen
    0.45
    POSITIVE LOGITS
     ৬০
    0.43
    ="#!"
    0.42
     ගන්න
    0.41
    こと
    0.40
    ১০
    0.39
    ή
    0.39
     inextricably
    0.38
    ****
    0.37
     Espírito
    0.37
    infty
    0.37
    Activations Density 0.503%

    No Known Activations