© 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. 17577
    Prev
    Next
    INDEX
    Explanations

    freak storm, Orange

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

    crisis lines or helplines

    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
     a
    0.60
    ة
    0.55
    <blockquote>
    0.54
    ية
    0.46
    2
    0.46
    ти
    0.45
    ა
    0.43
    ingar
    0.43
    ిన
    0.42
    ar
    0.41
    POSITIVE LOGITS
    Lots
    0.67
    Gson
    0.61
    Although
    0.61
    Unfortunately
    0.60
    Interesting
    0.60
    Dieses
    0.59
    ↳
    0.59
    Sung
    0.59
    Smaller
    0.57
    Time
    0.57
    Activations Density 0.021%

    No Known Activations