© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2554
    Prev
    Next
    INDEX
    Explanations

    sudden exclamations

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

    describing atmosphere and emotions

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

    text in non-English languages, particularly German, Spanish, Portuguese, and Russian.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @sripadkarne
    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
     மதிப்ப
    0.65
     தற்போது
    0.59
     याबाबत
    0.56
     குறிப்பிட்டு
    0.56
     அடிப்படையில்
    0.55
     বিভিন্ন
    0.54
     විශේෂ
    0.54
     ფუნქ
    0.54
     சிறப்பாக
    0.54
    ாகவும்
    0.53
    POSITIVE LOGITS
     nervously
    0.68
     plötzlich
    0.62
     раздра
    0.62
     majest
    0.61
     চিৎকার
    0.61
     cuch
    0.61
     бле
    0.59
    呻
    0.59
    忽然
    0.59
     olhando
    0.59
    Activations Density 0.017%

    No Known Activations