© 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. 1672
    Prev
    Next
    INDEX
    Explanations

    roads for, plugin sub

    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
    <unused963>
    1.44
    ”-
    1.44
    hattim
    1.42
    <unused1221>
    1.40
     Heater
    1.40
    <unused46>
    1.39
     heater
    1.38
    ﻣ
    1.36
    <unused1963>
    1.36
    <unused1209>
    1.36
    POSITIVE LOGITS
     propre
    0.90
     infine
    0.89
     propia
    0.85
     veremos
    0.84
     gibi
    0.83
     треть
    0.83
    guien
    0.82
     человек
    0.82
     группа
    0.82
    ast
    0.81
    Activations Density 0.401%

    No Known Activations