© 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. 95
    Prev
    Next
    INDEX
    Explanations

    model responses

    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
     intrinsic
    1.29
     hindering
    1.27
    <unused298>
    1.24
     inherently
    1.24
     adverse
    1.23
     absorb
    1.21
     curtail
    1.21
     hinder
    1.20
    <unused179>
    1.20
     gstlal
    1.20
    POSITIVE LOGITS
    <eos>
    1.09
     jornalista
    1.09
     destaque
    1.04
     dikutip
    1.03
     Consultado
    0.95
    ↵↵
    0.95
     vicepresidente
    0.93
     jeunesse
    0.93
     presidente
    0.91
     jî
    0.91
    Activations Density 1.097%

    No Known Activations