© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11910
    Prev
    Next
    INDEX
    Explanations

    You can do

    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_7_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
    ,_
    1.52
     Perché
    1.49
     homens
    1.44
     sacerdote
    1.41
     />,
    1.41
     Quadrupèdes
    1.39
    ম্মদ
    1.39
     morto
    1.39
    鸷
    1.39
     testacé
    1.39
    POSITIVE LOGITS
      
    1.38
    RP
    1.09
    ТЕ
    1.09
    !”.
    1.05
    เค
    1.05
    ZEN
    1.04
    !!!
    1.04
    е
    1.02
    とお
    1.02
    MAY
    1.02
    Activations Density 0.934%

    No Known Activations