© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9215
    Prev
    Next
    INDEX
    Explanations

    turn the tide

    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_22_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
    Leg
    1.06
     Leg
    1.04
     integral
    1.03
    leg
    1.02
     Prakt
    1.02
     Mac
    1.01
    Mac
    1.00
    
    0.95
    ากาศ
    0.94
    legen
    0.92
    POSITIVE LOGITS
    যদি
    0.97
     імен
    0.93
    ウェ
    0.92
    руя
    0.90
    낍
    0.90
    edd
    0.87
     conversaciones
    0.86
     once
    0.85
     mayors
    0.85
     piensan
    0.84
    Activations Density 0.000%

    No Known Activations