© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5494
    Prev
    Next
    INDEX
    Explanations

    starts of clauses or lists

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

    multilingual text or code explanations

    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
    var
    0.48
    usions
    0.41
    <eos>
    0.41
    oring
    0.39
    ums
    0.39
    gall
    0.39
    const
    0.38
    use
    0.38
    ivi
    0.38
    aires
    0.38
    POSITIVE LOGITS
    রাজের
    0.40
    也没
    0.40
    勰
    0.39
     supercritical
    0.39
     cui
    0.39
     bisschen
    0.38
     ఇది
    0.38
     miraculous
    0.38
     STUDY
    0.38
     তেলেভ
    0.38
    Activations Density 0.000%

    No Known Activations