© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 190
    Prev
    Next
    INDEX
    Explanations

    a followed by a word

    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
     a
    1.40
     to
    1.31
     and
    1.30
     is
    1.25
     that
    1.23
     the
    1.21
     it
    1.18
    ,
    1.17
     in
    1.13
     as
    1.09
    POSITIVE LOGITS
    egir
    1.23
    hmad
    1.22
     multitude
    1.14
    pathetic
    1.13
    𝘽
    1.13
    जनबी
    1.07
    போதும்
    1.06
    ربعة
    1.06
    国産
    1.06
    rizona
    1.05
    Activations Density 1.898%

    No Known Activations