© 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. 13208
    Prev
    Next
    INDEX
    Explanations

    issues, limitations, and claims

    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
    eko
    1.41
    孤
    1.33
     ceremonies
    1.33
    ihar
    1.31
    riko
    1.31
     rehearsal
    1.31
    ORMAL
    1.30
    槛
    1.28
    ეგის
    1.27
    交易
    1.27
    POSITIVE LOGITS
    ManyToManyField
    1.18
    Short
    1.17
     وف
    1.16
    ligare
    1.14
    Scores
    1.14
     Short
    1.10
     or
    1.10
    wide
    1.08
     short
    1.08
    short
    1.07
    Activations Density 0.000%

    No Known Activations