© 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. 13147
    Prev
    Next
    INDEX
    Explanations

    human dignity

    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
    Directions
    1.54
    Candidates
    1.44
     เพราะ
    1.43
    Benzyl
    1.37
     =-
    1.34
     ตรง
    1.33
    Carroll
    1.33
    Dougall
    1.28
    Addresses
    1.28
    Because
    1.28
    POSITIVE LOGITS
     tät
    1.56
    泊
    1.43
    দানি
    1.40
    ॉ
    1.36
     durchschnitt
    1.33
     numerosi
    1.31
    巻き
    1.30
    ेर
    1.29
    യും
    1.28
    झ
    1.28
    Activations Density 0.062%

    No Known Activations