© 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. 5054
    Prev
    Next
    INDEX
    Explanations

    explaining rationale

    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
    tile
    2.45
    rable
    2.40
    y
    2.38
    s
    2.29
     quel
    2.26
    dro
    2.26
    rú
    2.25
    t
    2.24
    nement
    2.22
    stroke
    2.21
    POSITIVE LOGITS
    ⿱
    2.57
    气的
    2.27
    ⿴
    2.27
    '>");
    2.25
    formatted
    2.24
    𝗍
    2.24
    吃
    2.20
    吃的
    2.19
    τι
    2.18
    istocene
    2.18
    Activations Density 0.261%

    No Known Activations