© 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. 1008
    Prev
    Next
    INDEX
    Explanations

    quoted phrase explained by "which"

    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
    稦
    1.15
    垁
    1.15
    甠
    1.12
    舧
    1.12
    瞔
    1.11
    覂
    1.05
    䅐
    1.05
    琕
    1.04
    秇
    1.03
    挔
    1.03
    POSITIVE LOGITS
     नामक
    1.34
     című
    1.28
     which
    1.28
     adlı
    1.22
    which
    1.18
     unveiled
    1.16
    라는
    1.14
     라는
    1.12
     launched
    1.12
     pioneered
    1.10
    Activations Density 1.385%

    No Known Activations