© 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. 13162
    Prev
    Next
    INDEX
    Explanations

    code imports

    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
    ly
    1.52
    kin
    1.32
    lyl
    1.15
     nuclear
    1.07
     breakfast
    1.04
    €™
    1.03
    lly
    1.03
     glasses
    1.03
    ally
    1.02
     suitable
    1.01
    POSITIVE LOGITS
    وسط
    1.56
     τι
    1.43
    臾
    1.42
    ᾗ
    1.41
     начале
    1.39
    쌔
    1.38
     való
    1.38
    несе
    1.37
     γεγον
    1.37
    ἃ
    1.35
    Activations Density 0.000%

    No Known Activations