© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7644
    Prev
    Next
    INDEX
    Explanations

    dilute with something

    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
     muitos
    2.31
     aparecen
    2.22
     propios
    2.21
     próprio
    2.14
     muchos
    2.12
     molti
    2.06
    ४
    2.06
    więks
    2.06
     elige
    2.06
    ónicos
    2.05
    POSITIVE LOGITS
    semble
    2.19
    ඪ
    2.13
     installment
    2.05
     inning
    1.95
    ாதாரண
    1.92
    startIndex
    1.91
     계
    1.89
    rayed
    1.86
    ihilation
    1.85
     αι
    1.85
    Activations Density 0.051%

    No Known Activations