© 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-65K
    7. 40473
    Prev
    Next
    INDEX
    Explanations

    evaluating potential and importance

    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_65k_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
    на
    0.55
    LEE
    0.54
     offrant
    0.54
    oteurs
    0.51
     τῶν
    0.50
     उत्कृष्ट
    0.49
     单
    0.49
     offrir
    0.48
     diretor
    0.48
     llevando
    0.48
    POSITIVE LOGITS
    飯
    0.46
     ग्रेटर
    0.46
    لل
    0.45
     belangrijk
    0.44
    的重要性
    0.43
    <=
    0.41
    }+
    0.41
    特点
    0.41
     belangrijke
    0.41
    副
    0.40
    Activations Density 0.002%

    No Known Activations