© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12361
    Prev
    Next
    INDEX
    Explanations

    clarifying questions followed by bullet points

    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
    cí
    2.55
     pena
    2.49
    či
    2.38
    िनी
    2.35
    弼
    2.33
    $/../../
    2.31
    nThe
    2.24
    lø
    2.24
    offs
    2.20
    otland
    2.19
    POSITIVE LOGITS
     poppies
    2.86
    臾
    2.86
    ен
    2.76
    𝗜
    2.75
    КУ
    2.74
     fabric
    2.69
    
    2.68
     modelBuilder
    2.66
    𝗮
    2.66
    𝗕
    2.65
    Activations Density 0.013%

    No Known Activations