© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11440
    Prev
    Next
    INDEX
    Explanations

    save, rain, morning, same

    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
    𝗻
    1.94
    to
    1.86
    lb
    1.86
    лец
    1.85
    𝗿
    1.83
    𝗮
    1.81
    𝗼
    1.80
    なく
    1.76
    𝐤
    1.75
    Claim
    1.74
    POSITIVE LOGITS
    াৰ
    2.33
    शुदा
    2.25
    pload
    2.20
    ി
    2.17
     parenchyma
    2.12
    衩
    2.11
    iunea
    2.09
    ಿಗಳು
    2.08
    a
    2.08
    îtier
    2.06
    Activations Density 0.046%

    No Known Activations