© 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. 1185
    Prev
    Next
    INDEX
    Explanations

    chosen focus

    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
    ämän
    1.77
    यानक
    1.74
     Hän
    1.70
    ᾧ
    1.68
    こちらも
    1.67
    ]].
    1.66
    <0x0C>
    1.63
    <table>
    1.62
     Cámara
    1.59
     affid
    1.59
    POSITIVE LOGITS
    ⅽ
    1.82
     maked
    1.70
     reh
    1.70
     thous
    1.65
     ach
    1.64
     picky
    1.61
     detrimental
    1.61
    깐
    1.61
     harmful
    1.60
    ස්ට
    1.59
    Activations Density 6.028%

    No Known Activations