© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11526
    Prev
    Next
    INDEX
    Explanations

    approach this

    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
    ม
    3.27
    нду
    3.00
    enary
    2.95
    มะ
    2.89
     তোলেন
    2.73
    t
    2.66
    わ
    2.65
    ン
    2.57
     sorte
    2.54
     знаходи
    2.50
    POSITIVE LOGITS
    OP
    2.55
     op
    2.53
    vius
    2.34
    ამო
    2.33
    ism
    2.31
    обходимо
    2.31
    cedented
    2.26
    пат
    2.21
    op
    2.18
    ங்கிணை
    2.18
    Activations Density 0.037%

    No Known Activations