© 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. 14100
    Prev
    Next
    INDEX
    Explanations

    epic action / online tools / tune of

    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
    嬛
    2.46
    갇
    2.37
    াসে
    2.33
    ವುದ
    2.32
    indd
    2.28
    stit
    2.26
    晗
    2.25
    ১৩
    2.16
    ution
    2.14
    ইল
    2.13
    POSITIVE LOGITS
    𝒅
    3.38
    𝒌
    3.37
    𝒑
    3.26
    𝒈
    3.22
    𝒔
    3.18
    𝒐
    3.13
    𝒕
    3.10
    𝒆
    3.04
    𝒊
    2.98
    𝒉
    2.92
    Activations Density 0.002%

    No Known Activations