© 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-65K
    7. 2588
    Prev
    Next
    INDEX
    Explanations

    confirmation, immediate support, thinking, leading, researched, correct classification, learning, funding, estimates

    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_65k_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
     polinom
    1.57
     Bibli
    1.45
    },(
    1.39
     soude
    1.39
     RasterModelGrid
    1.38
    <unused1478>
    1.38
     Parser
    1.36
    <unused1376>
    1.36
    <unused1400>
    1.36
    <unused1364>
    1.36
    POSITIVE LOGITS
     seemingly
    1.27
     purportedly
    1.22
     ostensibly
    1.13
     presumably
    1.08
     apparently
    1.08
     allegedly
    1.06
     virtually
    1.03
    ailing
    1.03
     increasingly
    1.02
     practically
    1.02
    Activations Density 1.469%

    No Known Activations