© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14555
    Prev
    Next
    INDEX
    Explanations

    resilience or affinity

    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_7_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
    𝘯
    3.62
    𝐥
    3.55
    𝐧
    3.49
    𝐦
    3.38
    𝘭
    3.32
    𝐩
    3.26
    𝐢
    3.25
    ু
    3.24
    𝐫
    3.19
    blit
    3.11
    POSITIVE LOGITS
    ์
    2.49
    s
    2.34
    ордина
    2.20
    tans
    2.13
    en
    2.09
    ‘
    2.00
     मोठ
    1.96
    ENAME
    1.94
    y
    1.94
    T
    1.91
    Activations Density 0.004%

    No Known Activations