© 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. 5844
    Prev
    Next
    INDEX
    Explanations

    code comments start

    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
    arrivalTime
    2.31
    ihilation
    2.22
    encodeWith
    2.21
    いの
    2.15
    ితీ
    2.14
     rum
    2.09
    铎
    2.08
     домаћинствима
    2.04
    colnames
    2.04
    \,.
    2.02
    POSITIVE LOGITS
    𝑠
    2.42
    𝑟
    2.35
    ोत्तम
    2.24
    ഗ്യ
    2.17
    istasis
    2.16
    𝑡
    2.15
    ēj
    2.14
    𝙩
    2.12
    রাস
    2.10
    𝙨
    2.10
    Activations Density 0.049%

    No Known Activations