© 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. 11493
    Prev
    Next
    INDEX
    Explanations

    Bastille, Epictetus

    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
    ‘
    2.60
    اً
    2.35
          
    2.34
       
    2.33
        
    2.32
     ‘
    2.25
    ’
    2.25
      
    2.23
    ’,
    2.16
    ’.
    2.06
    POSITIVE LOGITS
    Ӹ
    2.95
    pence
    2.92
     WPARAM
    2.91
    bidden
    2.90
    ሳሪያ
    2.86
    GAG
    2.83
    𝙥
    2.80
    ӳ
    2.72
    inputFields
    2.72
     codons
    2.69
    Activations Density 0.073%

    No Known Activations