© 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. 7-GEMMASCOPE-2-RES-16K
    4. 26
    Prev
    Next
    INDEX
    Explanations

    contractions like it's, you'll

    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
    𝒸
    1.44
    ‌‌
    1.40
    ‌
    1.36
    ⁢
    1.32
    𝑠
    1.30
    𝑖
    1.29
     می‌شود
    1.28
     می‌توان
    1.25
    痺
    1.24
    ስ
    1.24
    POSITIVE LOGITS
     }}$
    1.18
    oterapia
    1.17
    zy
    1.10
     }];
    1.08
    abilistic
    1.08
    "。
    1.07
    ateri
    1.06
    รก
    1.05
    hecy
    1.05
     baratos
    1.04
    Activations Density 0.225%

    No Known Activations