© 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. 2181
    Prev
    Next
    INDEX
    Explanations

    qualities and feelings of words

    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
    ává
    1.11
    ẹ
    1.10
    giờ
    1.09
    ávají
    1.07
    sinh
    1.07
    ớt
    1.06
    ly
    1.05
    '
    1.03
    unj
    1.03
    ъ
    1.02
    POSITIVE LOGITS
    ppling
    1.32
     rectify
    1.17
     inherently
    1.14
    烺
    1.12
     uphold
    1.12
     pleasurable
    1.11
     transcendence
    1.10
     inherent
    1.09
    িগণ
    1.08
     fruition
    1.08
    Activations Density 1.323%

    No Known Activations