© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1072
    Prev
    Next
    INDEX
    Explanations

    end of turn model

    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
     roaming
    2.46
     ל
    2.43
     ש
    2.38
     revived
    2.28
     resurrected
    2.25
     snacks
    2.25
     bruised
    2.24
     ecstasy
    2.23
     מ
    2.23
     scenic
    2.19
    POSITIVE LOGITS
    수
    2.65
    ラ
    2.58
    지
    2.48
    リ
    2.43
    か
    2.43
    위
    2.41
    보
    2.40
    부
    2.39
    유
    2.35
    カ
    2.34
    Activations Density 0.062%

    No Known Activations