© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5658
    Prev
    Next
    INDEX
    Explanations

    numbers like 10

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

    numbers related to ten

    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
     ৭৮
    0.44
     ৭৭
    0.44
     ২৯
    0.38
     ৩৬
    0.37
     ৫৫
    0.37
     sept
    0.37
     XVIII
    0.37
    <unused71>
    0.36
     XVII
    0.36
     ২২
    0.35
    POSITIVE LOGITS
     ten
    3.08
    十
    2.89
     Ten
    2.88
    Ten
    2.75
     दस
    2.63
     десять
    2.53
     ১০
    2.50
     १०
    2.48
     TEN
    2.44
     দশ
    2.42
    Activations Density 0.326%

    No Known Activations