© 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. 6858
    Prev
    Next
    INDEX
    Explanations

    twelve

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

    twelve

    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
     ត
    0.45
     ৫৮
    0.42
    7
    0.42
    ৭১
    0.41
     misc
    0.40
    ৫৮
    0.40
     Two
    0.38
    ៨
    0.38
    5
    0.38
     Raw
    0.37
    POSITIVE LOGITS
    十二
    1.02
     १२
    0.79
     ১২
    0.75
     twelve
    0.70
     zwölf
    0.69
    Twelve
    0.69
     बारह
    0.67
    ⑫
    0.65
     douze
    0.64
     Twelve
    0.61
    Activations Density 0.157%

    No Known Activations