© 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. 13701
    Prev
    Next
    INDEX
    Explanations

    URLs, names, and "desde"

    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
    EDE
    3.08
    ын
    2.99
    ୈ
    2.93
    लेक्ट
    2.89
     counselors
    2.85
     WPARAM
    2.82
    ExpNow
    2.81
    ானி
    2.77
    disc
    2.74
    giveness
    2.74
    POSITIVE LOGITS
    er
    3.27
    ς
    3.09
     lo
    3.01
    ੀ
    2.86
    рақ
    2.72
    년대
    2.61
    ీ
    2.49
    요
    2.40
    ería
    2.40
    eran
    2.40
    Activations Density 0.023%

    No Known Activations