© 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. 6627
    Prev
    Next
    INDEX
    Explanations

    AI, successor, attack, control

    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
    ゆう
    1.21
     vowed
    1.15
     도전
    1.14
     phi
    1.13
    빙
    1.12
     choisi
    1.11
     suaves
    1.10
    setVisible
    1.08
     alumn
    1.06
     Bally
    1.06
    POSITIVE LOGITS
     (>
    1.18
    őr
    1.17
    żyt
    1.15
    хло
    1.11
    uximab
    1.07
    Screenshot
    1.07
     دائما
    1.06
    íssimo
    1.05
    ország
    1.04
    вости
    1.03
    Activations Density 0.000%

    No Known Activations