© 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. 13425
    Prev
    Next
    INDEX
    Explanations

    first time in years

    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
    Not in Any Lists

    No Comments

    Negative Logits
    icier
    1.18
    !("{
    1.18
    !("{:
    1.11
     흥
    1.09
    pons
    1.09
    orks
    1.08
     distanciation
    1.07
     보호
    1.06
     분포
    1.06
    ப்ப
    1.06
    POSITIVE LOGITS
    #__
    1.09
    4
    1.09
    녕하십니까
    1.08
    5
    1.04
     Abit
    1.02
    otherm
    1.00
    8
    1.00
     سبيل
    0.98
     merito
    0.97
     XXV
    0.96
    Activations Density 0.080%

    No Known Activations