© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25234
    Prev
    Next
    INDEX
    Explanations

    predicting negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     банка
    0.45
    નિક
    0.41
    ığında
    0.40
    ẻ
    0.40
     растения
    0.38
    ग्व
    0.38
    Students
    0.38
    𝙥
    0.38
    міністра
    0.37
    જાર
    0.37
    POSITIVE LOGITS
     www
    0.44
     ×
    0.41
    ձ
    0.41
     sollic
    0.38
     Appel
    0.38
     xxx
    0.38
     Má
    0.38
     má
    0.37
     upper
    0.37
     Verónica
    0.37
    Activations Density 0.002%

    No Known Activations