© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2268
    Prev
    Next
    INDEX
    Explanations

    ethical dilemmas

    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_65k_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
     マット
    1.80
    ான்
    1.70
     മ
    1.66
     membre
    1.66
     septic
    1.65
     vekt
    1.62
     ブル
    1.61
     sensory
    1.57
     predictive
    1.57
     canopy
    1.56
    POSITIVE LOGITS
    be
    1.27
    ringing
    1.26
    bem
    1.24
    옵
    1.23
    proble
    1.21
    stream
    1.19
    abort
    1.19
    camb
    1.17
    ages
    1.15
    boxing
    1.14
    Activations Density 0.000%

    No Known Activations