© 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. 1049
    Prev
    Next
    INDEX
    Explanations

    spelling correction and foreign 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
     contributory
    1.24
     satisfactorily
    1.17
     ≥
    1.13
     sufficiently
    1.12
     adequately
    1.12
     <
    1.08
     arbitrarily
    1.07
     valid
    1.06
     simultaneously
    1.06
     rigorously
    1.06
    POSITIVE LOGITS
    ượu
    1.50
    ĕ
    1.44
    ガ
    1.44
    ác
    1.44
     Lobkovic
    1.44
    ụn
    1.44
    uh
    1.43
    ądź
    1.42
    kében
    1.42
    ukkig
    1.39
    Activations Density 0.569%

    No Known Activations