© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13867
    Prev
    Next
    INDEX
    Explanations

    Organization Name, ID, static

    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_7_width_16k_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
    akkhanam
    2.90
    akkhati
    2.84
     Containers
    2.76
    瘓
    2.75
    uddho
    2.72
    ские
    2.71
     Instances
    2.62
    ొప్ప
    2.61
    ujjati
    2.59
    Instances
    2.55
    POSITIVE LOGITS
    SIN
    1.67
    irr
    1.65
    it
    1.63
    ்க
    1.62
    ing
    1.58
    SCORE
    1.54
    ̀n
    1.54
     zoned
    1.54
    ਅ
    1.50
     dabei
    1.49
    Activations Density 0.002%

    No Known Activations