© 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. 2939
    Prev
    Next
    INDEX
    Explanations

    code block terminators

    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
    ඝ
    2.41
    𝓊
    2.33
    ઓ
    2.23
    τρ
    2.23
    asText
    2.20
    ೦
    2.17
    beiter
    2.15
     urząd
    2.14
     sämt
    2.13
     συνέχεια
    2.13
    POSITIVE LOGITS
    ↵↵
    3.90
    ↵
    3.65
    ↵↵↵
    2.38
    TAM
    2.21
     แต่
    2.17
     มัน
    2.12
    ↵↵↵↵
    2.08
     رام
    2.05
                                
    2.04
        
    2.00
    Activations Density 0.025%

    No Known Activations