© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12429
    Prev
    Next
    INDEX
    Explanations

    software command syntax

    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
    ↵↵
    1.25
    hibition
    1.12
    spapers
    1.10
     Therefore
    1.09
     That
    1.08
    ,
    1.05
    لم
    1.05
    There
    1.05
     There
    1.05
     This
    1.04
    POSITIVE LOGITS
    ajjati
    2.30
     regista
    2.19
     tamanho
    2.10
     algéb
    2.03
     MDET
    2.01
    拁
    1.99
    attamente
    1.97
    粔
    1.97
     vermelho
    1.96
    蛜
    1.95
    Activations Density 0.049%

    No Known Activations