© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2323
    Prev
    Next
    INDEX
    Explanations

    SMS, import, references, from

    np_acts-logits-general · gemini-2.5-flash-lite

    programming code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
     아멘
    0.29
    껍
    0.28
    한테
    0.28
     Obat
    0.27
     đón
    0.27
    줘
    0.27
     לו
    0.27
    ట్టు
    0.26
    Diameter
    0.26
    ँ
    0.26
    POSITIVE LOGITS
    if
    0.38
    late
    0.32
    let
    0.29
    later
    0.28
    governmental
    0.28
    try
    0.28
    دي
    0.27
    perhaps
    0.27
    csname
    0.27
    يرة
    0.27
    Activations Density 0.000%

    No Known Activations