© 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. 2069
    Prev
    Next
    INDEX
    Explanations

    revised approach

    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
     subtitles
    1.85
     referees
    1.65
     Carrot
    1.62
    ЕН
    1.61
     %\
    1.60
     НЕ
    1.60
    𝗟
    1.60
     %@
    1.59
     Pandas
    1.55
    У
    1.55
    POSITIVE LOGITS
    ’
    1.30
    indir
    1.25
    ‘
    1.23
    abwe
    1.16
    。“
    1.13
    itherto
    1.11
    reck
    1.10
     εμπ
    1.10
    孰
    1.07
     anew
    1.07
    Activations Density 0.000%

    No Known Activations