© 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. 12647
    Prev
    Next
    INDEX
    Explanations

    keys for list items

    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
     UNIX
    1.46
     startActivity
    1.41
     OFDM
    1.41
     linux
    1.41
    উল্লেখ
    1.34
     HEADER
    1.34
    hFile
    1.34
    (",");
    1.33
     SQLException
    1.32
    getExternal
    1.31
    POSITIVE LOGITS
    Fram
    1.48
    富
    1.36
    ோ
    1.23
    การ
    1.22
    Bra
    1.15
    lemon
    1.10
    Prés
    1.09
     зая
    1.09
     গাঁ
    1.08
    லாத
    1.08
    Activations Density 0.002%

    No Known Activations