© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14567
    Prev
    Next
    INDEX
    Explanations

    plural nouns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    𝐬
    0.71
    এস
    0.70
    𝒔
    0.70
    𝔰
    0.70
    스의
    0.70
    ્સ
    0.67
    ्स
    0.66
    সের
    0.65
    𝘀
    0.64
    sG
    0.64
    POSITIVE LOGITS
    ’-
    1.51
    ’,
    1.49
    ’
    1.45
    ’)
    1.36
    ’:
    1.30
    '-
    1.27
    ',
    1.26
    '/
    1.24
    '
    1.21
    ']
    1.20
    Activations Density 0.111%

    No Known Activations