© 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. 11208
    Prev
    Next
    INDEX
    Explanations

    SAMHSA National Helpline

    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
    ί
    2.16
    態
    2.02
     cinta
    2.01
    ih
    2.01
    :>
    1.91
     $\{\
    1.90
    껏
    1.89
     '\\;'
    1.87
    vata
    1.84
    ess
    1.84
    POSITIVE LOGITS
     která
    3.21
     illetve
    3.03
     która
    2.95
     który
    2.94
     jonka
    2.91
     ktorá
    2.86
     które
    2.86
    omitempty
    2.70
     valamint
    2.69
     který
    2.68
    Activations Density 0.007%

    No Known Activations