© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13001
    Prev
    Next
    INDEX
    Explanations

    understanding or obtaining actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ᅣ
    2.69
    ખા
    2.63
    ◞
    2.53
    स्तिष्क
    2.51
    ภัณฑ์
    2.50
    டைய
    2.50
     lend
    2.46
     partial
    2.43
    ᅭ
    2.42
     ries
    2.40
    POSITIVE LOGITS
    s
    3.03
    ാഗ
    2.89
    تون
    2.87
    ्ल
    2.74
    utan
    2.66
    ued
    2.65
     Ngf
    2.65
    giore
    2.63
    ༌
    2.63
    ္ဂ
    2.62
    Activations Density 1.057%

    No Known Activations