© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9826
    Prev
    Next
    INDEX
    Explanations

    directives now null

    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_13_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
    ;"
    1.53
     Raut
    1.49
    য়াছে
    1.48
    );"
    1.46
     kvinn
    1.45
     bezpeč
    1.43
    СТЬ
    1.42
     राजांनी
    1.42
     UserModel
    1.42
     daug
    1.41
    POSITIVE LOGITS
    <0x81>
    1.21
     out
    1.12
     inc
    1.08
    ounge
    1.08
     playlist
    1.07
     LLC
    1.05
     图
    1.03
     pose
    1.03
    ‬
    1.02
    out
    1.02
    Activations Density 0.000%

    No Known Activations