© 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. 2486
    Prev
    Next
    INDEX
    Explanations

    soundtracks for

    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
     Ira
    1.30
    SourceName
    1.26
    THIRD
    1.23
     repressed
    1.20
    زمانہ
    1.20
    ሱ
    1.17
    密切
    1.17
     পথে
    1.17
     धमा
    1.15
    ▃
    1.15
    POSITIVE LOGITS
     design
    1.28
    デザイン
    1.25
     diseño
    1.22
    piece
    1.14
     디자인
    1.13
     diseñada
    1.13
     desain
    1.11
    صميم
    1.08
     inlay
    1.07
    付き
    1.06
    Activations Density 0.730%

    No Known Activations