© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11416
    Prev
    Next
    INDEX
    Explanations

    need to

    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
    /
    1.22
     montagna
    1.10
     local
    0.97
     coord
    0.96
     lokale
    0.95
     abertura
    0.95
     যথ
    0.94
     pály
    0.93
     singoli
    0.93
    …
    0.92
    POSITIVE LOGITS
     necessitates
    1.52
     Undoubtedly
    1.51
    <unused1626>
    1.50
     comprehend
    1.50
    দিগের
    1.50
     hinders
    1.49
     Symptoms
    1.48
    SError
    1.46
     affects
    1.44
    <unused1216>
    1.43
    Activations Density 0.307%

    No Known Activations